Tootfinder

Berlin-based Motor Ai, which develops neuroscience-driven Level 4 autonomous driving tech and plans to deploy it on German roads in 2025, raised a $20M seed (Dean Takahashi/GamesBeat)
https://gamesbeat.com/after-8-years-motor-ai-raises-20m-for-autonom…

After 8 years, Motor Ai raises $20M for autonomous driving software
After eight years of work, Motor Ai has raised $20 million for autonomous driving software that prioritizes compliance.

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving
Luke Rowe, Rodrigue de Schaetzen, Roger Girgis, Christopher Pal, Liam Paull
https://arxiv.org/abs/2506.11234

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving
We present Poutine, a 3B-parameter vision-language model (VLM) tailored for end-to-end autonomous driving in long-tail driving scenarios. Poutine is trained in two stages. To obtain strong base driving capabilities, we train Poutine-Base in a self-supervised vision-language-trajectory (VLT) next-token prediction fashion on 83 hours of CoVLA nominal driving and 11 hours of Waymo long-tail driving. Accompanying language annotations are auto-generated with a 72B-parameter VLM. Poutine is obtained …

Extracting Realistic Pedestrian, Cycling, and Driving Street Networks from OpenStreetMap
https://isprs-archives.copernicus.org/articles/XLVIII-4-W13-2025/103/2025/

An Empirical study on LLM-based Log Retrieval for Software Engineering Metadata Management
Simin Sun, Yuchuan Jin, Miroslaw Staron
https://arxiv.org/abs/2506.11659

An Empirical study on LLM-based Log Retrieval for Software Engineering Metadata Management
Developing autonomous driving systems (ADSs) involves generating and storing extensive log data from test drives, which is essential for verification, research, and simulation. However, these high-frequency logs, recorded over varying durations, pose challenges for developers attempting to locate specific driving scenarios. This difficulty arises due to the wide range of signals representing various vehicle components and driving conditions, as well as unfamiliarity of some developers' with the…

RCG: Safety-Critical Scenario Generation for Robust Autonomous Driving via Real-World Crash Grounding
Benjamin Stoler, Juliet Yang, Jonathan Francis, Jean Oh
https://arxiv.org/abs/2507.10749

RCG: Safety-Critical Scenario Generation for Robust Autonomous Driving via Real-World Crash Grounding
Safety-critical scenarios are essential for training and evaluating autonomous driving (AD) systems, yet remain extremely rare in real-world driving datasets. To address this, we propose Real-world Crash Grounding (RCG), a scenario generation framework that integrates crash-informed semantics into adversarial perturbation pipelines. We construct a safety-aware behavior representation through contrastive pre-training on large-scale driving logs, followed by fine-tuning on a small, crash-rich dat…

I dislike Google but I find it hilarious that the author doesn't get that 50% of America - women - prefer not to get into a car with a total stranger.
☑️ You’ll Guffaw When You Hear How Much Self-Driving Waymos Cost Compared to Human-Driven Ubers
https://futurism.com/waymo-cost-uber

You’ll Guffaw When You Hear How Much Self-Driving Waymos Cost Compared to Human-Driven Ubers
The whole point of self-driving taxis is to cut costs — but Waymo doesn't appear to be any cheaper at all.

https://www.nbcnewyork.com/long-island/video-long-island-man-driving-to-work-handcuffed-by-ice-despite-being-citizen/6301068/

Video: NY man driving to work is handcuffed by ICE despite being a U.S. citizen
ICE detained a Brentwood electrician who is also a US citizen.

PolyTrack: try try again
PolyTrack is a Trackmania tribute - almost identical gameplay mechanics, but with digital controls, simplified driving model, and a very stripped-back graphical style. It's even simpler than Virtua Racing in many ways, with the car having a polygon count almost in the single digits. This simplicity means that it runs incredibly smoothly, even in-browser at Much like Trackmania, the courses are short but deceptively tricky to complete.

The last coffee in my favorite neighborhood spot in #Hanoi. 👋❤️
I will miss the Vietnamese vibe

So, driving home from a client call & up ahead of me on the freeway I see a giant blue pickup truck flying
4 count ‘em 4 giant flags behind the cab
I roll my eyes
Get a little closer…
Ok
US Flag
Massachusetts Flag
…progress Pride Flag
???Pride flag with “Don’t tread on me”
Did NOT expect that.

Analysis: Private-Label Products Are Driving Plant-Based Retail Sales Growth in Four European Countries https://vegconomist.com/market-and-trends/private-label-products-driving-plant-based-retail-sales-growth-four-eu…

Analysis: Private-Label Products Are Driving Plant-Based Retail Sales Growth in Four European Countries - vegconomist - the vegan business magazine
GFI Europe has analysed previously unpublished Circana data, finding that cheaper private label products led to a growth in plant-based retail sales volumes

Full Professor Position, of Environmental Biogeochemistry of Metals, at Division of Environmental Geosciences, Uni Vienna (@edge-vienna.bsky.social) #geology #Austria #Österreich

We are hiring: Full Professor of Environmental Biogeochemistry of Metals
Human activities are driving rapid environmental change on a global scale, with pollutants playing a critical role in pushing planetary systems beyond safe limits. These changes have profound consequences for biodiversity, ecosystem functioning, and human health.

Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis
Yuan Gao, Mattia Piccinini, Yuchen Zhang, Dingrui Wang, Korbinian Moller, Roberto Brusnicki, Baha Zarrouki, Alessio Gambi, Jan Frederik Totz, Kai Storms, Steven Peters, Andrea Stocco, Bassam Alrifaee, Marco Pavone, Johannes Betz
https://

Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis
For autonomous vehicles, safe navigation in complex environments depends on handling a broad range of diverse and rare driving scenarios. Simulation- and scenario-based testing have emerged as key approaches to development and validation of autonomous driving systems. Traditional scenario generation relies on rule-based systems, knowledge-driven models, and data-driven synthesis, often producing limited diversity and unrealistic safety-critical cases. With the emergence of foundation models, wh…

While we have the Corsa currently in for investigation into possible OBC failure, my wife's been driving the family estate, and has been complaining about the thickness of the steering wheel[1].
Extrapolating a bit, here's where I think we might be headed:
[1] A 2019 G31. I think subsequent models have got worse, so perhaps this extrapolation isn't far off?
#bmw

driving through a forest in a national park with no service and I get this. what sorta black mirror shit is going on here. I’m gonna go down gosner and a demon is gonna get me

Cam Ward gives thanks to dad, who drove him all over Texas to help him reach his dreams https://www.espn.com/nfl/story/_/id/45493280/tennessee-titans-qb-cameron-ward-fathers-day-message-calvin

No playing Spanish-language music: Many immigrants say they have new rules for driving : NPR
https://www.npr.org/2025/07/12/nx-s1-5437957/no-playing-spanish-language-music-many-immigrants-say-they-have-new-rules-for-driving

Bedrock Robotics raised $80M from Eclipse and 8VC to develop retrofit self-driving kits for construction and worksite vehicles, in testing with five companies (Kirsten Korosec/TechCrunch)
https://techcrunch.com/2025/07/16/ex-way…

Ex-Waymo engineers launch Bedrock Robotics with $80M to automate construction | TechCrunch
Former Waymo engineers have launched an autonomous vehicle startup with $80 million in venture funds.

Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation
Zhen Xu, Hongyu Zhou, Sida Peng, Haotong Lin, Haoyu Guo, Jiahao Shao, Peishan Yang, Qinglin Yang, Sheng Miao, Xingyi He, Yifan Wang, Yue Wang, Ruizhen Hu, Yiyi Liao, Xiaowei Zhou, Hujun Bao
https://arxiv.org/abs/2507.11540

Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation
Depth estimation is a fundamental task in 3D computer vision, crucial for applications such as 3D reconstruction, free-viewpoint rendering, robotics, autonomous driving, and AR/VR technologies. Traditional methods relying on hardware sensors like LiDAR are often limited by high costs, low resolution, and environmental sensitivity, limiting their applicability in real-world scenarios. Recent advances in vision-based methods offer a promising alternative, yet they face challenges in generalizatio…

Detecting AI Assistance in Abstract Complex Tasks
Tyler King, Nikolos Gurney, John H. Miller, Volkan Ustun
https://arxiv.org/abs/2507.10761 https://…

Detecting AI Assistance in Abstract Complex Tasks
Detecting assistance from artificial intelligence is increasingly important as they become ubiquitous across complex tasks such as text generation, medical diagnosis, and autonomous driving. Aid detection is challenging for humans, especially when looking at abstract task data. Artificial neural networks excel at classification thanks to their ability to quickly learn from and process large amounts of data -- assuming appropriate preprocessing. We posit detecting help from AI as a classificatio…

Your Ride, Your Rules: Psychology and Cognition Enabled Automated Driving Systems
Zhipeng Bao, Qianwen Li
https://arxiv.org/abs/2506.11842 https://

Your Ride, Your Rules: Psychology and Cognition Enabled Automated Driving Systems
Despite rapid advances in autonomous driving, current autonomous vehicles (AVs) lack effective bidirectional communication with occupants, limiting personalization and recovery from immobilization. This reduces comfort and trust, potentially slowing broader AV adoption. We propose PACE-ADS (Psychology and Cognition Enabled Automated Driving Systems), a human-centered autonomy framework that enables AVs to sense, interpret, and respond to both external traffic and internal occupant states. PACE-…

I believe I have managed to prove my ID in order to comply with the new laws that say I have to prove my ID to own the business I own that I'm sure already asked me to prove my ID when I registered it.
First we tried the on-web version, but that apparently relies upon the corporates having managed to profile and track me, because it told me they had no questions upon which to base identification. Good I guess? My avoid-tracking systems must be working at least a bit?
Next we tried the android app, but apparently the phone I tried that with is too old and the app won't install.
So next option is turning up at a post office with a printed letter. I don't own a printer though, so had to have them post that to me.
Took the letter and a driving licence up to the post office today and "It's not going through" they said, pointing to a stalled progress bar on an android app on a tablet.
Um. Okay. So?
Just wait longer apparently. About ten minutes and it finally proceeded and the post office man took a photograph of me after asking me to disrobe of my robe, strip down to a teeshirt and jeans.
Not sure in what sense this has proven my ID any more than it was already proven to get the driving licence or company registration in the first place?
Apparently I now have government logins for "One Login" and for "government gateway" and they are not the same thing? But sort of are the same thing?
Can't say I really understand it. Expect they'll introduce a third government login when they do these Digital ID cards they're talking about.
God knows how I'm supposed to know which to use when the company tax records need updating in a few months.
#id #government #oneLogin

I missed one of everything while I was deployed to Afghanistan:
Birthdays. Holidays. Recitals. Soccer games.
I missed my husband. I missed our 5 kids even more.
After I returned to Colorado, we were driving home one day when my husband suggested we get two $5 pizzas from Little Caesar’s.
Sitting at the table, I felt an immense sense of gratitude to finally be together again,
just enjoying a simple meal.
"Wow," I told my husband. "This was …

Rear Admiral Eileen Laubacher | Democrat for Congress
Rear Admiral Eileen Laubacher, a candidate for Congress in Colorado’s 4th District, is on a new mission after a lifetime of service: Defeat Lauren Boebert.

I feel like computers are getting more like cars, or... how I view cars.
I do not need/want to spend a ton of money to get everything computerized car with ever sensor and camera and screen there is because I just don't think I need it or it's worth it for how much I drive.
I get that some people want that, and should probably have it, but I've got like 35 years of driving experience and I think I do okay.

The Strategic Imperative for Healthcare Organizations to Build Proprietary Foundation Models
Naresh Tiwari
https://arxiv.org/abs/2506.11412 https://…

The Strategic Imperative for Healthcare Organizations to Build Proprietary Foundation Models
This paper presents a comprehensive analysis of the strategic imperative for healthcare organizations to develop proprietary foundation models rather than relying exclusively on commercial alternatives. We examine four fundamental considerations driving this imperative: the domain-specific requirements of healthcare data representation, critical data sovereignty and governance considerations unique to healthcare, strategic competitive advantages afforded by proprietary AI infrastructure, and th…

Vaseline. Vaseline (or, indeed, lip balm) on the lenses works a treat. Causes no lasting damage but places the vehicle out of use for some time. https://www.theguardian.com/technology/2025/jun/10/uber-uk-trial-of-self…

Maryland suspends 20,000 drivers licenses per year because of unpaid child support. And how many does it suspend because of bad driving?
https://www.thebaltimorebanner.com/pol…

Maryland lawmakers scale back driver’s license suspensions for unpaid child support
The measure exempts Marylanders making at or 250% below the federal poverty guidelines.

Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving
Wonung Kim, Yubin Lee, Yoonsung Kim, Jinwoo Hwang, Seongryong Oh, Jiyong Jung, Aziz Huseynov, Woong Gyu Park, Chang Hyun Park, Divya Mahajan, Jongse Park
https://arxiv.org/abs/2507.10178

Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving
Transformers are the driving force behind today's Large Language Models (LLMs), serving as the foundation for their performance and versatility. Yet, their compute and memory costs grow with sequence length, posing scalability challenges for long-context inferencing. In response, the algorithm community is exploring alternative architectures, such as state space models (SSMs), linear attention, and recurrent neural networks (RNNs), which we refer to as post-transformers. This shift presents a k…

Black-Box Edge AI Model Selection with Conformal Latency and Accuracy Guarantees
Anders E. Kal{\o}r, Tomoaki Ohtsuki
https://arxiv.org/abs/2506.11391 https…

Black-Box Edge AI Model Selection with Conformal Latency and Accuracy Guarantees
Edge artificial intelligence (AI) will be a central part of 6G, with powerful edge servers supporting devices in performing machine learning (ML) inference. However, it is challenging to deliver the latency and accuracy guarantees required by 6G applications, such as automated driving and robotics. This stems from the black-box nature of ML models, the complexities of the tasks, and the interplay between transmitted data quality, chosen inference model, and the random wireless channel. This pap…

Work-in-Progress: Multi-Deadline DAG Scheduling Model for Autonomous Driving Systems
Atsushi Yano, Takuya Azumi
https://arxiv.org/abs/2505.06780 https://…

Work-in-Progress: Multi-Deadline DAG Scheduling Model for Autonomous Driving Systems
Autoware is an autonomous driving system implemented on Robot Operation System (ROS) 2, where an end-to-end timing guarantee is crucial to ensure safety. However, existing ROS 2 cause-effect chain models for analyzing end-to-end latency struggle to accurately represent the complexities of Autoware, particularly regarding sync callbacks, queue consumption patterns, and feedback loops. To address these problems, we propose a new scheduling model that decomposes the end-to-end timing constraints o…

Classical algorithm inspired by the feedback-based algorithm for quantum optimization and local counterdiabatic driving
Takuya Hatomura
https://arxiv.org/abs/2506.09214

Classical algorithm inspired by the feedback-based algorithm for quantum optimization and local counterdiabatic driving
We propose a quantum-inspired classical algorithm for combinatorial optimization problems, named the counterdiabaticity-assisted classical algorithm for optimization (CACAO). In this algorithm, a solution of a given combinatorial optimization problem is heuristically searched with classical spin dynamics based on quantum Lyapunov control of local counterdiabatic driving. We compare the performance of CACAO with that of quantum time-evolution algorithms, i.e., quantum annealing, the feedback-bas…

Tokopedia sellers say Tokopedia's strengths have eroded since its TikTok Shop merger in Indonesia, driving thousands of sellers to join rivals, including Toco (Michelle Anindya/Rest of World)
https://restofworld.org/2025/tiktok-indonesia-tokopedia-merger-problems…

TikTok’s messy merger in Indonesia could be a preview of what’s to come in the U.S.
A year after merging with local giant Tokopedia, TikTok’s business model is alienating sellers, forcing many to join rival platforms.

The metric from energy-momentum non-conservation: Generalizing Noether and completing spectral geometry
Achim Kempf
https://arxiv.org/abs/2506.11186 https:…

The metric from energy-momentum non-conservation: Generalizing Noether and completing spectral geometry
We complete the program of spectral geometry, in the sense that we show that a manifold's shape, i.e., its metric, can be reconstructed from its resonant sound when tapped lightly, i.e., from its spectrum, -- if in addition we also record the resonances' mutual excitation pattern when the driving is strong enough to reach the nonlinear regime. Applied to spacetime, this finding yields a generalization of Noether's theorem: the specific pattern of energy-momentum non-conservation on a generic cu…

Hydrodynamical simulations of the vertical shear instability with dynamic dust and cooling rates in protoplanetary disks
Yuya Fukuhara, Mario Flock, Satoshi Okuzumi, Ryosuke T. Tominaga
https://arxiv.org/abs/2507.11156

Hydrodynamical simulations of the vertical shear instability with dynamic dust and cooling rates in protoplanetary disks
Turbulence in protoplanetary disks affects dust evolution and planetesimal formation. The vertical shear instability (VSI) is one of the candidate turbulence-driving mechanisms in the outer disk region. Since the VSI requires rapid gas cooling, dust grains in disks can influence and potentially control VSI-driven turbulence. However, VSI-driven turbulence has strong vertical motion, causing vertical dust diffusion. As a result, it remains unclear how turbulent structures and dust distributions …

Impact of Cosmic Ray-driven Outflows on Lyman-$\alpha$ Emission in Cosmological Simulations
Taysun Kimm, Julien Devriendt, Francesco Rodriguez Montero, Adrianne Slyz, Jeremy Blaizot, Harley Katz, Beomchan Koh, Hyunmi Song
https://arxiv.org/abs/2507.10805

Impact of Cosmic Ray-driven Outflows on Lyman-$α$ Emission in Cosmological Simulations
Cosmic ray (CR) feedback has been proposed as a powerful mechanism for driving warm gas outflows in galaxies. We use cosmological magnetohydrodynamic simulations to investigate the impact of CR feedback on neutral hydrogen (HI) in a $10^{11}\,M_\odot$ dark matter halo at $2

Robustness of Floquet topological phase at room temperature: a first-principles dynamics study
Ruiyi Zhou, Yosuke Kanai
https://arxiv.org/abs/2506.12005 ht…

Robustness of Floquet topological phase at room temperature: a first-principles dynamics study
Nonadiabatic Thouless pumping of electrons is studied within the framework of topological Floquet engineering, particularly focused on how atomic lattice dynamics affect the emergent Floquet topological phase in trans-polyacetylene under the driving electric field. As similarly done in the earlier work [Zhou and Kanai, J. Phys. Chem. Lett., 12, 4496 (2021)], the real-time time-dependent density functional theory and Ehrenfest dynamics simulations were used to investigate the extent to which the…

Ratchet Effects in Cyclic Pattern Formation Systems with Competing Interactions
C. Reichhardt, C. J. O. Reichhardt
https://arxiv.org/abs/2507.10824 https:/…

Ratchet Effects in Cyclic Pattern Formation Systems with Competing Interactions
Ratchet effects can appear for particles interacting with an asymmetric potential under ac driving or for a thermal system in which a substrate is periodically flashed. Here, we show that a new type of collective ratchet effect can arise for a pattern-forming system coupled to an asymmetric substrate when the interaction potential between the particles is periodically oscillated in order to cycle the system through different patterns. We consider particles with competing short-range attraction …

Cowboys All-Pro arrested for allegedly driving 97 MPH with gun in back seat https://www.pennlive.com/sports/2025/07/cowboys-all-pro-arrested-for-allegedly-driving-97-mph-with-gun-in-back-seat.html

#nokings #usa #usapol
"Thousands of people have begun demonstrating across the US as part of the “No Kings” protests. Millions are expected to turn up for events against the Trump administration at ro…

Random rotational invariance of integration by parts formulas within a Bismut-type approach
Susanna Deh\`o, Francesco C. De Vecchi, Paola Morando, Stefania Ugolini
https://arxiv.org/abs/2506.11937

Random rotational invariance of integration by parts formulas within a Bismut-type approach
The stochastic rotational invariance of an integration by parts formula inspired by the Bismut approach to Malliavin calculus is proved in the framework of the Lie symmetry theory of stochastic differential equations. The non-trivial effect of the rotational invariance of the driving Brownian motion in the derivation of the integration by parts formula is discussed and the invariance property of the formula is shown via applications to some explicit two-dimensional Brownian motion-driven stocha…

With the 5th #AAS246 presser come the paper https://arxiv.org/abs/2506.07262 (ALMA-JELLY I: High Resolution CO(2-1) Observations of Ongoing Ram Pressure Stripping in NGC 4858 Reveal Asymmetrical Gas Tail Formation and Fallback), the press release https://news.arizona.edu/news/belly-beast-massive-clumps-reveal-star-factories-bygone-era-cosmos (In the belly of the beast: massive clumps reveal star factories from a bygone era of the cosmos) and the papers https://iopscience.iop.org/article/10.3847/1538-4357/ada8a6 (UNCOVERing the Faint End of the z ∼ 7 [O iii] Luminosity Function with JWST's F410M Medium Bandpass Filter) with the press release https://science.nasa.gov/missions/webb/nasas-webb-uncovers-galaxy-population-driving-cosmic-renovation/ and https://arxiv.org/abs/2505.06198 (The "Dark-Matter Dominated" Galaxy Segue 1 Modeled with a Black Hole and no Dark Halo) with the press release https://www.utsa.edu/today/2025/06/story/researchers-offer-alternative-to-dark-matter-model.html

Subharmonic Shapiro steps in depinning dynamics of a 2D solid dusty plasma modulated by 1D nonlinear deformed periodic substrates
Zhaoye Wang, Nichen Yu, Ao xu, Chen Liang, C. Reichhardt, C. J. O. Reichhardt, Yan Feng
https://arxiv.org/abs/2507.11389

Subharmonic Shapiro steps in depinning dynamics of a 2D solid dusty plasma modulated by 1D nonlinear deformed periodic substrates
Langevin dynamical simulations are performed to investigate the depinning dynamics of a two-dimensional solid dusty plasma, which is modulated by one-dimensional nonlinear deformed periodic substrates, and also driven by the combination of the DC and AC forces. As the DC driving force increases gradually, pronounced subharmonic and harmonic Shapiro steps are discovered under the combined modulation of the deformed substrate and the external AC drive. These observed subharmonic and harmonic Shap…

Machine learning for in-situ composition mapping in a self-driving magnetron sputtering system
Sanna Jarl, Jens Sj\"olund, Robert J. W. Frost, Anders Holst, Jonathan J. S. Scragg
https://arxiv.org/abs/2506.05999

Machine learning for in-situ composition mapping in a self-driving magnetron sputtering system
Self-driving labs (SDLs), employing automation and machine learning (ML) to accelerate experimental procedures, have enormous potential in the discovery of new materials. However, in thin film science, SDLs are mainly restricted to solution-based synthetic methods which are easier to automate but cannot access the broad chemical space of inorganic materials. This work presents an SDL based on magnetron co-sputtering. We are using combinatorial frameworks, obtaining accurate composition maps on …

Dealogic: tech deals accounted for $421B of the $1.67T in global deals announced in the first five months of 2025, with 75% of tech M&A involving AI software (Milana Vinn/Reuters)
https://www.reuters.com/business/unglamoro

This is the future #Republicans want for you and your children

Chinese companies' incentive is simple: "Don't lose market share, and future markets are included."
https://www.bbc.co.uk/future/article/20250530-how-electric-scooters-are-driving-chinas-salt-battery-push…

How electric scooters are driving China's salt battery push
The country is racing ahead of the rest of the world in bringing sodium-ion batteries to the mass market. This time, through scooters.

Soliton self-excitation under pulsed driving in a Kerr resonator
Matthew Macnaughtan, Zongda Li, Yiqing Xu, Xiaoming Wei, Zhongmin Yang, St\'ephane Coen, Miro Erkintalo, Stuart G. Murdoch
https://arxiv.org/abs/2506.10307

Soliton self-excitation under pulsed driving in a Kerr resonator
We present a novel regime of cavity soliton excitation in a Kerr resonator driven by a train of desynchronised pulses. In this regime, the soliton solution is shown to be the sole available state for the intracavity field, allowing for the automatic excitation of single solitons without the application of any external perturbations or parameter ramping. The self-excitation of cavity soliton frequency combs is validated through numerical continuation of the Lugiato-Lefever equation, direct numer…

Driving in the rain

Causal Hamilton-Jacobi-Bellman Equations for Anticipative Stochastic Optimal Control
Peter Bank, Franziska Bielert
https://arxiv.org/abs/2507.08657 https:/…

Causal Hamilton-Jacobi-Bellman Equations for Anticipative Stochastic Optimal Control
We consider a stochastic optimal control problem where the controller can anticipate the evolution of the driving noise over some dynamically changing time window. The controlled state dynamics are understood as a rough differential equation. We combine the martingale optimality principle with a functional form of Itô's formula to derive a Hamilton-Jacobi-Bellman (HJB) equation for this problem. This HJB equation is formulated in terms of Dupire's functional derivatives and involves a transpor…

Google pulls 352 apps from the Play Store that were part of an ad fraud scheme behind 1.5B daily bid requests and whose estimated impact is in the seven-figures (Kendra Barnett/Adweek)
https://www.adweek.com/programmatic/google

Google Wipes 350 Android Apps Tied to Ad Fraud Driving 1.5B Daily Bid Requests
Traffic generated by the IconAds scheme primarily originated from Brazil, Mexico, and the U.S.

SMART-Merge Planner: A Safe Merging and Real-Time Motion Planner for Autonomous Highway On-Ramp Merging
Toktam Mohammadnejad, Jovin D'sa, Behdad Chalaki, Hossein Nourkhiz Mahjoub, Ehsan Moradi-Pari
https://arxiv.org/abs/2507.10968

SMART-Merge Planner: A Safe Merging and Real-Time Motion Planner for Autonomous Highway On-Ramp Merging
Merging onto a highway is a complex driving task that requires identifying a safe gap, adjusting speed, often interactions to create a merging gap, and completing the merge maneuver within a limited time window while maintaining safety and driving comfort. In this paper, we introduce a Safe Merging and Real-Time Merge (SMART-Merge) planner, a lattice-based motion planner designed to facilitate safe and comfortable forced merging. By deliberately adapting cost terms to the unique challenges of f…

This https://arxiv.org/abs/2505.06780 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csOS_…

Work-in-Progress: Multi-Deadline DAG Scheduling Model for Autonomous Driving Systems
Autoware is an autonomous driving system implemented on Robot Operation System (ROS) 2, where an end-to-end timing guarantee is crucial to ensure safety. However, existing ROS 2 cause-effect chain models for analyzing end-to-end latency struggle to accurately represent the complexities of Autoware, particularly regarding sync callbacks, queue consumption patterns, and feedback loops. To address these problems, we propose a new scheduling model that decomposes the end-to-end timing constraints o…

MoSE: Skill-by-Skill Mixture-of-Expert Learning for Autonomous Driving
Lu Xu, Jiaqian Yu, Xiongfeng Peng, Yiwei Chen, Weiming Li, Jaewook Yoo, Sunghyun Chunag, Dongwook Lee, Daehyun Ji, Chao Zhang
https://arxiv.org/abs/2507.07818

MoSE: Skill-by-Skill Mixture-of-Expert Learning for Autonomous Driving
Recent studies show large language models (LLMs) and vision language models (VLMs) trained using web-scale data can empower end-to-end autonomous driving systems for a better generalization and interpretation. Specifically, by dynamically routing inputs to specialized subsets of parameters, the Mixture-of-Experts (MoE) technique enables general LLMs or VLMs to achieve substantial performance improvements while maintaining computational efficiency. However, general MoE models usually demands ext…

Meta launches V-JEPA 2, an open-source AI "world model" to understand and predict 3D environments and object movements, to help robotics and self-driving cars (Ryan Browne/CNBC)
https://www.cnbc.com/2025/06/11/meta-launc

Meta launches AI 'world model' to advance robotics, self-driving cars
Meta on Wednesday announced it's rolling out a new AI "world model" that can better understand the 3D environment and movements of physical objects.

Riding around with Kid1 last night, I remarked that many of the drivers, who seemed more agitated than normal, were "ornery." I explained what the word meant and he said, "I think 'hornery' better describes it." We now have a term for a specific form of dangerous driving.
#BikeTooter #cycling

I mean… protected bike lanes as a double win? Sure!
“We’ve taken a strong and visible approach to the problem of speeding and reckless driving... That’s also why we’ve installed so many protected bike lanes. One of the goals is to prevent speeders from passing on the right.”

Mayor Cavalier Johnson: ‘A leader has to stand up and lead even if some residents are not happy’
Nearly four years into the Milwaukee Mayor’s job, Cavalier Johnson, at only 38, wears the mayor’s mantle like a favorite pullover as he talks policing, crime and housing in Milwaukee.

Bans Are Driving Up Later Abortions
https://jessica.substack.com/p/bans-are-driving-up-later-abortions

Causality-aware Safety Testing for Autonomous Driving Systems
Wenbing Tang, Mingfei Cheng, Renzhi Wang, Yuan Zhou, Chengwei Liu, Yang Liu, Zuohua Ding
https://arxiv.org/abs/2506.08688

Causality-aware Safety Testing for Autonomous Driving Systems
Simulation-based testing is essential for evaluating the safety of Autonomous Driving Systems (ADSs). Comprehensive evaluation requires testing across diverse scenarios that can trigger various types of violations under different conditions. While existing methods typically focus on individual diversity metrics, such as input scenarios, ADS-generated motion commands, and system violations, they often fail to capture the complex interrelationships among these elements. This oversight leads to ga…

Chris Landry has a green card.
Lived in the US since he was 3 years old.
But, "In 2004 and 2007, Landry faced charges of marijuana possession and driving w a suspended license... suspended sentence & paid his fines."
"never thought that that would threaten my status"
https://www.nbcnews.com/ne…

N.H. green card holder denied re-entry to U.S. after visiting native Canada
The man, who supported President Donald Trump though he can't vote, says he "feels differently" now and blames the administration for his immigration plight.

On expected #V2G returns: “Given the Netherlands’ more strained grid, Faton believes savings will be even higher there.”
Tough bet in a country where grid operators provide no financial incentives to residential customers to shift demand, let alone support the local grid with V2G.

'Utrecht Energized' launched: How bidirectional charging is set to make the breakthrough - electrive.com
Bidirectional charging is often hailed as the holy grail of e-mobility. The batteries of electric cars are not only used for driving but can also power homes

I didn't expect a future where self-driving electric cars would spew nazi rants like somebody's crazy uncle.
https://www.usatoday.com/story/money/cars/2025/07/10/elon-musk-grok-tesla-vehicles/84535654007/

Fired Justice Department official warns we are "driving straight into an abyss" (Scott Macfarlane/CBS News)
https://www.cbsnews.com/news/fired-justice-department-official-we-are-falling-into-an-abyss/
http://www.memeorandum.com/250710/p138#a250710p138

Strong squeezing and perfect one-way EPR steering in electro-optomechanical system
Qing-Min Zeng, A-Peng Liu, Qi Guo
https://arxiv.org/abs/2507.07697 https…

Strong squeezing and perfect one-way EPR steering in electro-optomechanical system
We consider a three-mode electro-optomechanical system in which a mechanical oscillator is coupled to an optical cavity and a LC circuit through radiation pressure and capacitive coupling, respectively. By controlling the two-tone driving of the optical cavity and the microwave driving of the LC circuit, the strong squeezing of both the microwave field of the LC circuit and the mechanical mode will be obtained. Moreover, by further altering the driving power of the system, the perfect one-way E…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/3]:
- SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving
Honghao Fu, Yongli Gu, Yidong Yan, Yilang Shen, Yiwen Wu, Libo Sun

#nokings #usa #usapol
Der Guardian hat es als zweites Titelthems, gleich unter dem Israelisch-Iranischen Konflikt als Aufmacher.
Und im Pressebild taucht der 'inflatable Donald" mit den Wi…

Towards more efficient quantitative safety validation of residual risk for assisted and automated driving
Daniel Betschinske, Malte Schrimpf, Steven Peters, Kamil Klonecki, Jan Peter Karch, Moritz Lippert
https://arxiv.org/abs/2506.10363

Towards more efficient quantitative safety validation of residual risk for assisted and automated driving
The safety validation of Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS) increasingly demands efficient and reliable methods to quantify residual risk while adhering to international standards such as ISO 21448. Traditionally, Field Operational Testing (FOT) has been pivotal for macroscopic safety validation of automotive driving functions up to SAE automation level 2. However, state-of-the-art derivations for empirical safety demonstrations using FOT often result …

Drove through the Blackwall Tunnel to Greenwich and back to Islington yesterday.
South of the river it's all 30MPH speed limits and everything feels too fast and scary compared to the sedate and pedestrian-friendly 20MPH limits in the north.
Since I last went through it, it seems the Blackwall tunnel has added a toll.
The TFL website for setting up to pay the tolls is absolutely awful. Failed in Librewolf, Failed in Firefox. Failed because VPN. Took me four attempts in three different browsers to get it to take payment card details.
Demands *no* special characters in the password?!? And doesn't even tell you what the specific problem with the password is, just "doesn't meet the rules above"
Uses awful validation questions like "mothers maiden name". Bad enough practice to use them at all, but the "memorable date" question restricts to ddmmyy format so you can't even put in a date from outside this century.
For some reason asks for a PIN and and Password both!? Pointless. Then actually refuses the login form if you supply both!?

Setting up the auto-payment doesn't seem to have covered the charges added to the registration plate yesterday, so had to do the payment-details entering yet again to deal with yesterday's charges.
Email validation message contains the link only in the HTML of the email, not the text version, so viewed in Mutt it has no link.
And this all seems to be separate from the Dartford Crossing charge, which had a less crappy but still pretty crappy signup.
Good god council programmers suck at web-dev.
#driving #london #tfl #blackwallTunnel #greenwich

Never mind the dummy,
The Robotaxi also failed to stop for the stop sign.
Nice hit and run afterwards, though.
https://bsky.app/profile/carlquintanilla.bsky.social/post/3lridgcwvvc2n

Unreal is all you need: Multimodal ISAC Data Simulation with Only One Engine
Kongwu Huang, Shiyi Mu, Jun Jiang, Yuan Gao, Shugong Xu
https://arxiv.org/abs/2507.08716

Unreal is all you need: Multimodal ISAC Data Simulation with Only One Engine
Scaling laws have achieved success in LLM and foundation models. To explore their potential in ISAC research, we propose Great-X. This single-engine multimodal data twin platform reconstructs the ray-tracing computation of Sionna within Unreal Engine and is deeply integrated with autonomous driving tools. This enables efficient and synchronized simulation of multimodal data, including CSI, RGB, Radar, and LiDAR. Based on this platform, we construct an open-source, large-scale, low-altitude UAV …

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[3/4]:
- Boundary-Guided Trajectory Prediction for Road Aware and Physically Feasible Autonomous Driving
Ahmed Abouelazm, Mianzhi Liu, Christian Hubschneider, Yin Wu, Daniel Slieter, J. Marius Z\"ollner

‘Open prison’: The forced labour driving India’s $5 trillion economy dream | Labour Rights | Al Jazeera
https://www.aljazeera.com/features/2025/6/7/open-prison-the-forced-labour-driving-indias-5-trillion-economy-dream?traffic_source=rss

InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching
Yilun Wang, Pengfei Chen, Haiyu Huang, Zilong He, Gou Tan, Chuanfu Zhang, Jingkai He, Zibin Zheng
https://arxiv.org/abs/2507.08523

InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching
Modern software systems generate massive volumes of runtime logs, necessitating efficient and accurate log parsing to enable critical downstream tasks such as anomaly detection and root cause analysis. Recently, large language models (LLMs) have achieved advanced accuracy on log parsing, but their deployment in production environments faces two major limitations: (1) the privacy risks associated with commercial LLMs, driving the adoption of local deployment, and (2) the stringent latency and th…

Florida Governor Ron DeSantis has said Floridians have a right to hit protesters with their car if they need to "flee for your safety."
DeSantis was speaking on The Rubin Report on Wednesday when he said:
"We also have a policy that if you're driving on one of those streets and a mob comes and surrounds your vehicle,
and threatens you, you have a right to flee for your safety.
"And so if you drive off and you hit one of these people,
tha…

Ron DeSantis Says Floridians Have Right to Hit Protesters With Cars
"That's their fault for impinging on you," Florida's governor said.

Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving
Haochen Liu, Tianyu Li, Haohan Yang, Li Chen, Caojun Wang, Ke Guo, Haochen Tian, Hongchen Li, Hongyang Li, Chen Lv
https://arxiv.org/abs/2506.09800

Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving
End-to-end autonomous driving has emerged as a promising paradigm for directly mapping sensor inputs to planning maneuvers using learning-based modular integrations. However, existing imitation learning (IL)-based models suffer from generalization to hard cases, and a lack of corrective feedback loop under post-deployment. While reinforcement learning (RL) offers a potential solution to tackle hard cases with optimality, it is often hindered by overfitting to specific driving cases, resulting i…

Observation of Power Superbroadening of Spectral Line Profiles on IBM Quantum
Ivo S. Mihov, Nikolay V. Vitanov
https://arxiv.org/abs/2506.08748 https://

Observation of Power Superbroadening of Spectral Line Profiles on IBM Quantum
Power broadening refers to the widening of the spectral line profile in a two-state quantum transition as the strength of the driving field increases. This phenomenon commonly arises in continuous-wave driving when the radiation field's intensity exceeds the transition's saturation intensity and it has been extensively studied in spectroscopy. For pulsed-field excitation, the spectral response of the quantum system may differ significantly: while a rectangular-shaped pulse leads to a linear pow…

STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving
Christian Fruhwirth-Reisinger, Du\v{s}an Mali\'c, Wei Lin, David Schinagl, Samuel Schulter, Horst Possegger
https://arxiv.org/abs/2506.06218

STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving
We introduce STSBench, a scenario-based framework to benchmark the holistic understanding of vision-language models (VLMs) for autonomous driving. The framework automatically mines pre-defined traffic scenarios from any dataset using ground-truth annotations, provides an intuitive user interface for efficient human verification, and generates multiple-choice questions for model evaluation. Applied to the NuScenes dataset, we present STSnu, the first benchmark that evaluates the spatio-temporal …

Comparison of Localization Algorithms between Reduced-Scale and Real-Sized Vehicles Using Visual and Inertial Sensors
Tobias Kern, Leon Tolksdorf, Christian Birkner
https://arxiv.org/abs/2507.11241

Comparison of Localization Algorithms between Reduced-Scale and Real-Sized Vehicles Using Visual and Inertial Sensors
Physically reduced-scale vehicles are emerging to accelerate the development of advanced automated driving functions. In this paper, we investigate the effects of scaling on self-localization accuracy with visual and visual-inertial algorithms using cameras and an inertial measurement unit (IMU). For this purpose, ROS2-compatible visual and visual-inertial algorithms are selected, and datasets are chosen as a baseline for real-sized vehicles. A test drive is conducted to record data of reduced-…

China releases draft guidelines on cross-border transmission of automobile data, which could pave the way for the wider rollout of Tesla's FSD in the country (Bloomberg)
https://www.bloomberg.com/news/articles/20

TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems
You Lu, Dingji Wang, Kaifeng Huang, Bihuan Chen, Xin Peng
https://arxiv.org/abs/2507.05932

TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems
Autonomous vehicle technology has been developed in the last decades with recent advances in sensing and computing technology. There is an urgent need to ensure the reliability and robustness of autonomous driving systems (ADSs). Despite the recent achievements in testing various ADS modules, little attention has been paid on the automated testing of traffic light detection models in ADSs. A common practice is to manually collect and label traffic light data. However, it is labor-intensive, and…

Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Driving
Akshar Tumu, Henrik I. Christensen, Marcell Vazquez-Chanlatte, Chikao Tsuchiya, Dhaval Bhanderi
https://arxiv.org/abs/2506.10317

Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Driving
Lane-topology prediction is a critical component of safe and reliable autonomous navigation. An accurate understanding of the road environment aids this task. We observe that this information often follows conventions encoded in natural language, through design codes that reflect the road structure and road names that capture the road functionality. We augment this information in a lightweight manner to SMERF, a map-prior-based online lane-topology prediction model, by combining structured road…

Overtone Rabi oscillation of optically polarized triplet electron spins and nuclear hyperpolarization in powder
Koichiro Miyanishi, Takuya F. Segawa, Makoto Negoro, Akinori Kagawa, Kazuyuki Takeda
https://arxiv.org/abs/2506.10498

Overtone Rabi oscillation of optically polarized triplet electron spins and nuclear hyperpolarization in powder
We report coherent overtone Rabi oscillations of optically-polarized triplet electron spins and nuclear hyperpolarization in powder samples at room temperature. The strong orientation dependence through the zero-field splitting (ZFS) interaction in the single-quantum transition is overcome by coherently driving the significantly narrower overtone transition. Analytical formulas for the overtone lineshape and nutation functions for axially symmetric ZFS interactions are derived. Overtone Rabi os…

Unprecedented wealth concentration
– and the unbridled power that comes with such wealth
– has distorted our democracy and is driving societal and economic tensions.
Musk, the world’s richest man, wields power no one person should have.
He has used this power to elect candidates that will enact policies to protect his interests and he even bought his way into government.
While at the helm of Doge, Musk dramatically reshaped the government in ways that benefit him…

Estimating the Joint Probability of Scenario Parameters with Gaussian Mixture Copula Models
Christian Reichenb\"acher, Philipp Rank, Jochen Hipp, Oliver Bringmann
https://arxiv.org/abs/2506.10098

Estimating the Joint Probability of Scenario Parameters with Gaussian Mixture Copula Models
This paper presents the first application of Gaussian Mixture Copula Models to the statistical modeling of driving scenarios for the safety validation of automated driving systems. Knowledge of the joint probability distribution of scenario parameters is essential for scenario-based safety assessment, where risk quantification depends on the likelihood of concrete parameter combinations. Gaussian Mixture Copula Models bring together the multimodal expressivity of Gaussian Mixture Models and the…

From Marginal to Joint Predictions: Evaluating Scene-Consistent Trajectory Prediction Approaches for Automated Driving
Fabian Konstantinidis, Ariel Dallari Guerreiro, Raphael Trumpp, Moritz Sackmann, Ulrich Hofmann, Marco Caccamo, Christoph Stiller
https://arxiv.org/abs/2507.05254

From Marginal to Joint Predictions: Evaluating Scene-Consistent Trajectory Prediction Approaches for Automated Driving
Accurate motion prediction of surrounding traffic participants is crucial for the safe and efficient operation of automated vehicles in dynamic environments. Marginal prediction models commonly forecast each agent's future trajectories independently, often leading to sub-optimal planning decisions for an automated vehicle. In contrast, joint prediction models explicitly account for the interactions between agents, yielding socially and physically consistent predictions on a scene level. However…

Elon Musk says Tesla's robotaxi service will "tentatively" begin on June 22 in Austin, with first autonomous deliveries of a car to a customer's home on June 28 (Ari Levy/CNBC)
https://www.cnbc.com/2025/06/10/elon-musk-

Elon Musk says Tesla robotaxi rides in Austin 'tentatively' set to begin June 22
Tesla CEO Elon Musk said in a post on X on Tuesday that the first self-driving Tesla will reach a customer's house on June 28.

Diffusion Models for Safety Validation of Autonomous Driving Systems
Juanran Wang, Marc R. Schlichting, Harrison Delecki, Mykel J. Kochenderfer
https://arxiv.org/abs/2506.08459

Diffusion Models for Safety Validation of Autonomous Driving Systems
Safety validation of autonomous driving systems is extremely challenging due to the high risks and costs of real-world testing as well as the rarity and diversity of potential failures. To address these challenges, we train a denoising diffusion model to generate potential failure cases of an autonomous vehicle given any initial traffic state. Experiments on a four-way intersection problem show that in a variety of scenarios, the diffusion model can generate realistic failure samples while capt…

Ego-centric Learning of Communicative World Models for Autonomous Driving
Hang Wang, Dechen Gao, Junshan Zhang
https://arxiv.org/abs/2506.08149 https://

Ego-centric Learning of Communicative World Models for Autonomous Driving
We study multi-agent reinforcement learning (MARL) for tasks in complex high-dimensional environments, such as autonomous driving. MARL is known to suffer from the \textit{partial observability} and \textit{non-stationarity} issues. To tackle these challenges, information sharing is often employed, which however faces major hurdles in practice, including overwhelming communication overhead and scalability concerns. By making use of generative AI embodied in world model together with its latent …

LeAD: The LLM Enhanced Planning System Converged with End-to-end Autonomous Driving
Yuhang Zhang, Jiaqi Liu, Chengkai Xu, Peng Hang, Jian Sun
https://arxiv.org/abs/2507.05754

LeAD: The LLM Enhanced Planning System Converged with End-to-end Autonomous Driving
A principal barrier to large-scale deployment of urban autonomous driving systems lies in the prevalence of complex scenarios and edge cases. Existing systems fail to effectively interpret semantic information within traffic contexts and discern intentions of other participants, consequently generating decisions misaligned with skilled drivers' reasoning patterns. We present LeAD, a dual-rate autonomous driving architecture integrating imitation learning-based end-to-end (E2E) frameworks with l…

Photos and partial footage of an FSD-enabled Tesla sideswiping a parked vehicle and hitting a woman in November 2023 shows FSD's limits; the NHTSA is probing it (Bloomberg)
https://www.bloomberg.com/features/2025-tesla-full-self-driving-crash/…

Sources: Uber is in talks with Travis Kalanick to help fund his acquisition of Pony.ai's US arm; Pony.ai has permits to operate robo taxis in the US and China (Mike Isaac/New York Times)

Uber in Talks With Travis Kalanick to Fund Self-Driving Car Deal
The ride-hailing company is in talks to help Mr. Kalanick, who was forced out in 2017, purchase an autonomous vehicles start-up as robot taxi service Waymo gains momentum.

Towards Safe Autonomous Driving: A Real-Time Safeguarding Concept for Motion Planning Algorithms
Korbinian Moller, Rafael Neher, Marvin Seegert, Johannes Betz
https://arxiv.org/abs/2507.07444

Towards Safe Autonomous Driving: A Real-Time Safeguarding Concept for Motion Planning Algorithms
Ensuring the functional safety of motion planning modules in autonomous vehicles remains a critical challenge, especially when dealing with complex or learning-based software. Online verification has emerged as a promising approach to monitor such systems at runtime, yet its integration into embedded real-time environments remains limited. This work presents a safeguarding concept for motion planning that extends prior approaches by introducing a time safeguard. While existing methods focus on …

Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving
Guizhe Jin, Zhuoren Li, Bo Leng, Ran Yu, Lu Xiong
https://arxiv.org/abs/2506.23771

Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving
Reinforcement Learning (RL) is increasingly used in autonomous driving (AD) and shows clear advantages. However, most RL-based AD methods overlook policy structure design. An RL policy that only outputs short-timescale vehicle control commands results in fluctuating driving behavior due to fluctuations in network outputs, while one that only outputs long-timescale driving goals cannot achieve unified optimality of driving behavior and control. Therefore, we propose a multi-timescale hierarchica…

Using Diffusion Ensembles to Estimate Uncertainty for End-to-End Autonomous Driving
Florian Wintel, Sigmund H. H{\o}eg, Gabriel Kiss, Frank Lindseth
https://arxiv.org/abs/2506.00560

Using Diffusion Ensembles to Estimate Uncertainty for End-to-End Autonomous Driving
End-to-end planning systems for autonomous driving are improving rapidly, especially in closed-loop simulation environments like CARLA. Many such driving systems either do not consider uncertainty as part of the plan itself, or obtain it by using specialized representations that do not generalize. In this paper, we propose EnDfuser, an end-to-end driving system that uses a diffusion model as the trajectory planner. EnDfuser effectively leverages complex perception information like fused camera …

Online Performance Assessment of Multi-Source-Localization for Autonomous Driving Systems Using Subjective Logic
Stefan Orf, Sven Ochs, Marc Ren\'e Zofka, J. Marius Z\"ollner
https://arxiv.org/abs/2506.02932

Online Performance Assessment of Multi-Source-Localization for Autonomous Driving Systems Using Subjective Logic
Autonomous driving (AD) relies heavily on high precision localization as a crucial part of all driving related software components. The precise positioning is necessary for the utilization of high-definition maps, prediction of other road participants and the controlling of the vehicle itself. Due to this reason, the localization is absolutely safety relevant. Typical errors of the localization systems, which are long term drifts, jumps and false localization, that must be detected to enhance s…

This https://arxiv.org/abs/2502.20636 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Delayed-Decision Motion Planning in the Presence of Multiple Predictions
Reliable automated driving technology is challenged by various sources of uncertainties, in particular, behavioral uncertainties of traffic agents. It is common for traffic agents to have intentions that are unknown to others, leaving an automated driving car to reason over multiple possible behaviors. This paper formalizes a behavior planning scheme in the presence of multiple possible futures with corresponding probabilities. We present a maximum entropy formulation and show how, under certai…

Self driving algorithm for an active four wheel drive racecar
Gergely Bari, Laszlo Palkovics
https://arxiv.org/abs/2506.06077 https://

Self driving algorithm for an active four wheel drive racecar
Controlling autonomous vehicles at their handling limits is a significant challenge, particularly for electric vehicles with active four wheel drive (A4WD) systems offering independent wheel torque control. While traditional Vehicle Dynamics Control (VDC) methods use complex physics-based models, this study explores Deep Reinforcement Learning (DRL) to develop a unified, high-performance controller. We employ the Proximal Policy Optimization (PPO) algorithm to train an agent for optimal lap tim…

DriveMind: A Dual-VLM based Reinforcement Learning Framework for Autonomous Driving
Dawood Wasif, Terrence J Moore, Chandan K Reddy, Jin-Hee Cho
https://arxiv.org/abs/2506.00819

DriveMind: A Dual-VLM based Reinforcement Learning Framework for Autonomous Driving
End-to-end autonomous driving systems map sensor data directly to control commands, but remain opaque, lack interpretability, and offer no formal safety guarantees. While recent vision-language-guided reinforcement learning (RL) methods introduce semantic feedback, they often rely on static prompts and fixed objectives, limiting adaptability to dynamic driving scenes. We present DriveMind, a unified semantic reward framework that integrates: (i) a contrastive Vision-Language Model (VLM) encoder…

3DGS_LSR:Large_Scale Relocation for Autonomous Driving Based on 3D Gaussian Splatting
Haitao Lu, Haijier Chen, Haoze Liu, Shoujian Zhang, Bo Xu, Ziao Liu
https://arxiv.org/abs/2507.05661

3DGS_LSR:Large_Scale Relocation for Autonomous Driving Based on 3D Gaussian Splatting
In autonomous robotic systems, precise localization is a prerequisite for safe navigation. However, in complex urban environments, GNSS positioning often suffers from signal occlusion and multipath effects, leading to unreliable absolute positioning. Traditional mapping approaches are constrained by storage requirements and computational inefficiency, limiting their applicability to resource-constrained robotic platforms. To address these challenges, we propose 3DGS-LSR: a large-scale relocaliz…

AWML: An Open-Source ML-based Robotics Perception Framework to Deploy for ROS-based Autonomous Driving Software
Satoshi Tanaka, Samrat Thapa, Kok Seang Tan, Amadeusz Szymko, Lobos Kenzo, Koji Minoda, Shintaro Tomie, Kotaro Uetake, Guolong Zhang, Isamu Yamashita, Takamasa Horibe
https://arxiv.org/abs/2506.00645

AWML: An Open-Source ML-based Robotics Perception Framework to Deploy for ROS-based Autonomous Driving Software
In recent years, machine learning technologies have played an important role in robotics, particularly in the development of autonomous robots and self-driving vehicles. As the industry matures, robotics frameworks like ROS 2 have been developed and provides a broad range of applications from research to production. In this work, we introduce AWML, a framework designed to support MLOps for robotics. AWML provides a machine learning infrastructure for autonomous driving, supporting not only the …

DRO-EDL-MPC: Evidential Deep Learning-Based Distributionally Robust Model Predictive Control for Safe Autonomous Driving
Hyeongchan Ham, Heejin Ahn
https://arxiv.org/abs/2507.05710

DRO-EDL-MPC: Evidential Deep Learning-Based Distributionally Robust Model Predictive Control for Safe Autonomous Driving
Safety is a critical concern in motion planning for autonomous vehicles. Modern autonomous vehicles rely on neural network-based perception, but making control decisions based on these inference results poses significant safety risks due to inherent uncertainties. To address this challenge, we present a distributionally robust optimization (DRO) framework that accounts for both aleatoric and epistemic perception uncertainties using evidential deep learning (EDL). Our approach introduces a novel…