The paper proves W[1]-hardness parameterized by dimension d for positivity, zonotope containment, max approximation, and L_p-Lipschitz constants in 2- and 3-layer ReLU networks, showing enumeration methods are optimal under ETH.
hub Mixed citations
End to End Learning for Self-Driving Cars
Mixed citation behavior. Most common role is background (50%).
86
Pith papers citing it
3,114
external citations · Pith
Background
50% of classified citations
abstract
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system learns to drive in traffic on local roads with or without lane markings and on highways. It also operates in areas with unclear visual guidance such as in parking lots and on unpaved roads. The system automatically learns internal representations of the necessary processing steps such as detecting useful road features with only the human steering angle as the training signal. We never explicitly trained it to detect, for example, the outline of roads. Compared to explicit decomposition of the problem, such as lane marking detection, path planning, and control, our end-to-end system optimizes all processing steps simultaneously. We argue that this will eventually lead to better performance and smaller systems. Better performance will result because the internal components self-optimize to maximize overall system performance, instead of optimizing human-selected intermediate criteria, e.g., lane detection. Such criteria understandably are selected for ease of human interpretation which doesn't automatically guarantee maximum system performance. Smaller networks are possible because the system learns to solve the problem with the minimal number of processing steps. We used an NVIDIA DevBox and Torch 7 for training and an NVIDIA DRIVE(TM) PX self-driving car computer also running Torch 7 for determining where to drive. The system operates at 30 frames per second (FPS).
hub tools
citation-role summary
background 9
method 4
other 1
citation-polarity summary
representative citing papers
Diffusion Policy models robot actions as a conditional diffusion process, outperforming prior state-of-the-art methods by 46.9% on average across 12 manipulation tasks from four benchmarks.
ContextShift benchmark on COCO reveals up to 227% more false negatives and 44% fewer predictions under controlled context changes, non-monotonic NPMI response, and gains from context-aware augmentation.
LOSCAR-SGD combines local updates, sparse model averaging, and communication-computation overlap with a delay-corrected merge rule, providing convergence rates for smooth non-convex objectives under worker heterogeneity.
Ringmaster LMO extends delay-thresholding from ASGD to LMO-based momentum updates, providing convergence guarantees under (L0, L1)-smoothness and time-complexity bounds that recover optimal rates in the Euclidean case.
4DLidarOpen is a new open dataset providing synchronized 4D FMCW Lidar velocity measurements, multi-Lidar and camera data, and 3D bounding-box annotations with track IDs to support benchmarks on 3D detection, BEV segmentation, flow prediction, and motion forecasting.
Bench2Drive-Robust is a new closed-loop benchmark that evaluates end-to-end autonomous driving models under deployment perturbations from camera failures, ego-state errors, and compute delays, showing substantial performance degradation beyond image-level tests.
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
TCD-Arena is a new customizable testing framework that runs millions of experiments to map how 33 different assumption violations affect time series causal discovery methods and shows ensembles can boost overall robustness.
A training-free method using Fourier-parameterized star-convex contours optimized via gradients to generate compact, faithful visual attributions for image classifiers on benchmarks like ImageNet.
DSRL steers pretrained diffusion policies for robotics by applying RL to their latent noise inputs, achieving sample-efficient real-world adaptation with only black-box access.
Proposes Safety-Aware Mutation Testing (SAMT) that derives mutant generation rules from STPA to simulate realistic interaction failures between ADS modules.
A tensor-based batch fuzzing framework with adaptive perturbation scaling from specification ranges achieves up to 40X higher throughput and 4X more detected violations than sequential baselines on DNN benchmarks.
Develops infinite-horizon stationary robust mean-field games incorporating distributional uncertainty, proves equilibrium existence via fixed-point on contractive Bellman operator, gives convergent algorithm, and derives finite-population approximation bounds under contractive regime.
Conditioning adversarial driving-scenario generation on XAI-derived policy failure evidence yields larger post-retraining success-rate gains than ChatScene or LLM-Attacker across multiple AV models.
Self-play in a vector simulator trains a driving teacher; a vision student aligned by action and low-rank structural losses drives end-to-end without expert trajectory supervision.
TOAD applies test-time Cross-Entropy Method optimization to refine trajectories using the planner's scorer as a reward function, improving end-to-end autonomous driving performance without retraining.
Double preconditioning (DoPr) improves downstream task performance in test-time feedback settings without consistent gains in validation loss.
Safe2Drive benchmark and SDS metric reveal that state-of-the-art E2E autonomous driving models suffer large drops in driving and safety scores on common hazard scenarios compared to standard benchmarks.
NTR adds a self-distillation masked latent reconstruction objective that uses only scene tokens to reconstruct masked patch features, improving visual representation quality and planning performance in end-to-end autonomous driving.
Introduces partial multi-neuron relaxation using existing branching heuristics to balance bound tightness and scalability in neural network verification, with integration into Marabou showing positive experimental comparisons.
EXACT-MPPI embeds an analytic signed-distance evaluator for polygonal footprints into an MPPI controller to produce footprint-aware motion commands from raw point clouds without maps or training.
ReasonBreak demonstrates up to 89% attack success on reasoning and 72% on trajectories in NVIDIA Alpamayo VLA models via black-box textual perturbations, introducing a reasoning-aware evaluation framework and benchmark for autonomous driving.
Dywave uses wavelet hierarchical decomposition to create event-aligned compact token sequences for heterogeneous IoT signals, yielding up to 12% accuracy gains and 75% shorter inputs on mainstream sequence models across five datasets.
citing papers explorer
-
Parameterized Hardness of Zonotope Containment and Neural Network Verification
The paper proves W[1]-hardness parameterized by dimension d for positivity, zonotope containment, max approximation, and L_p-Lipschitz constants in 2- and 3-layer ReLU networks, showing enumeration methods are optimal under ETH.
-
Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
Diffusion Policy models robot actions as a conditional diffusion process, outperforming prior state-of-the-art methods by 46.9% on average across 12 manipulation tasks from four benchmarks.
-
ContextShift: A Controlled Benchmark for Context Dependence in Object Detection
ContextShift benchmark on COCO reveals up to 227% more false negatives and 44% fewer predictions under controlled context changes, non-monotonic NPMI response, and gains from context-aware augmentation.
-
LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging
LOSCAR-SGD combines local updates, sparse model averaging, and communication-computation overlap with a delay-corrected merge rule, providing convergence rates for smooth non-convex objectives under worker heterogeneity.
-
Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method
Ringmaster LMO extends delay-thresholding from ASGD to LMO-based momentum updates, providing convergence guarantees under (L0, L1)-smoothness and time-complexity bounds that recover optimal rates in the Euclidean case.
-
4DLidarOpen: An Open 4D FMCW Lidar Dataset for Motion-Aware Autonomous Driving
4DLidarOpen is a new open dataset providing synchronized 4D FMCW Lidar velocity measurements, multi-Lidar and camera data, and 3D bounding-box annotations with track IDs to support benchmarks on 3D detection, BEV segmentation, flow prediction, and motion forecasting.
-
Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations
Bench2Drive-Robust is a new closed-loop benchmark that evaluates end-to-end autonomous driving models under deployment perturbations from camera failures, ego-state errors, and compute delays, showing substantial performance degradation beyond image-level tests.
-
Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
-
TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations
TCD-Arena is a new customizable testing framework that runs millions of experiments to map how 33 different assumption violations affect time series causal discovery methods and shows ensembles can boost overall robustness.
-
Extremal Contours: Gradient-driven contours for compact visual attribution
A training-free method using Fourier-parameterized star-convex contours optimized via gradients to generate compact, faithful visual attributions for image classifiers on benchmarks like ImageNet.
-
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
DSRL steers pretrained diffusion policies for robotics by applying RL to their latent noise inputs, achieving sample-efficient real-world adaptation with only black-box access.
-
Towards Safety-Aware Mutation Testing for Autonomous Driving Systems
Proposes Safety-Aware Mutation Testing (SAMT) that derives mutant generation rules from STPA to simulate realistic interaction failures between ADS modules.
-
Tensor-Based Batch Fuzzing with Adaptive Perturbation Scaling for Deep Neural Networks
A tensor-based batch fuzzing framework with adaptive perturbation scaling from specification ranges achieves up to 40X higher throughput and 4X more detected violations than sequential baselines on DNN benchmarks.
-
Stationary Robust Mean-Field Games under Model Mismatches
Develops infinite-horizon stationary robust mean-field games incorporating distributional uncertainty, proves equilibrium existence via fixed-point on contractive Bellman operator, gives convergent algorithm, and derives finite-population approximation bounds under contractive regime.
-
SPHINX: First Explain, Then Explore
Conditioning adversarial driving-scenario generation on XAI-derived policy failure evidence yields larger post-retraining success-rate gains than ChatScene or LLM-Attacker across multiple AV models.
-
TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations
Self-play in a vector simulator trains a driving teacher; a vision student aligned by action and low-rank structural losses drives end-to-end without expert trajectory supervision.
-
Test-Time Trajectory Optimization for Autonomous Driving
TOAD applies test-time Cross-Entropy Method optimization to refine trajectories using the planner's scorer as a reward function, improving end-to-end autonomous driving performance without retraining.
-
Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss
Double preconditioning (DoPr) improves downstream task performance in test-time feedback settings without consistent gains in validation loss.
-
Safe2Drive: Evaluating Safe Driving Behaviors of E2E Autonomous Driving Models
Safe2Drive benchmark and SDS metric reveal that state-of-the-art E2E autonomous driving models suffer large drops in driving and safety scores on common hazard scenarios compared to standard benchmarks.
-
NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving
NTR adds a self-distillation masked latent reconstruction objective that uses only scene tokens to reconstruct masked patch features, improving visual representation quality and planning performance in end-to-end autonomous driving.
-
Neural Network Verification using Partial Multi-Neuron Relaxation
Introduces partial multi-neuron relaxation using existing branching heuristics to balance bound tightness and scalability in neural network verification, with integration into Marabou showing positive experimental comparisons.
-
EXACT-MPPI: Exact Signed-Distance Navigation for Arbitrary-Footprint Robots from Point Clouds via Path Integral Control
EXACT-MPPI embeds an analytic signed-distance evaluator for polygonal footprints into an MPPI controller to produce footprint-aware motion commands from raw point clouds without maps or training.
-
ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving
ReasonBreak demonstrates up to 89% attack success on reasoning and 72% on trajectories in NVIDIA Alpamayo VLA models via black-box textual perturbations, introducing a reasoning-aware evaluation framework and benchmark for autonomous driving.
-
Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signals
Dywave uses wavelet hierarchical decomposition to create event-aligned compact token sequences for heterogeneous IoT signals, yielding up to 12% accuracy gains and 75% shorter inputs on mainstream sequence models across five datasets.
-
Temporal Sampling Frequency Matters: A Capacity-Aware Study of End-to-End Driving Trajectory Prediction
Smaller end-to-end autonomous driving models achieve optimal 3-second trajectory prediction accuracy at lower or intermediate temporal sampling frequencies, whereas larger VLA-style models perform best at the highest frequencies across Waymo, nuScenes, and PAVE datasets.
-
Optimality of Sub-network Laplace Approximations: New Results and Methods
Sub-network Laplace approximations always underestimate an idealized predictive variance, and the proposed gradient- and greedy-based parameter selection rules provably close that gap better than existing heuristics.
-
Ensemble Distributionally Robust Bayesian Optimisation with Continuous Context
EDRBO uses ensemble surrogates and Wasserstein ambiguity sets to robustify BO acquisition functions against context distribution mismatch, with sublinear regret O(γ_T √T) and SOTA empirical results on continuous contexts.
-
ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
ReflectDrive-2 combines masked discrete diffusion with RL-aligned self-editing to generate and refine driving trajectories, reaching 91.0 PDMS on NAVSIM camera-only and 94.8 in best-of-6.
-
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
OGPO enables sample-efficient full-finetuning of generative control policies via off-policy critics and modified PPO, achieving SOTA on robot manipulation tasks while rescuing poorly initialized behavior cloning policies without expert data.
-
Empirical Insights of Test Selection Metrics under Multiple Testing Objectives and Distribution Shifts
A broad empirical benchmark shows how 15 existing test selection metrics perform for fault detection, performance estimation, and retraining under corrupted, adversarial, temporal, natural, and label shifts across image, text, and Android data.
-
FingerViP: Learning Real-World Dexterous Manipulation with Fingertip Visual Perception
FingerViP equips each finger with a miniature camera and trains a multi-view diffusion policy that achieves 80.8% success on real-world dexterous tasks previously limited by wrist-camera occlusion.
-
MVAdapt: Zero-Shot Multi-Vehicle Adaptation for End-to-End Autonomous Driving
MVAdapt conditions end-to-end autonomous driving policies on explicit vehicle physics to achieve better zero-shot transfer and few-shot calibration across different vehicles in CARLA simulation.
-
Scaling-Aware Data Selection for End-to-End Autonomous Driving Systems
MOSAIC is a scaling-aware data selection framework that outperforms baselines in training end-to-end autonomous driving planners, achieving comparable or better EPDMS scores with up to 80% less data.
-
Safety-Aligned 3D Object Detection: Single-Vehicle, Cooperative, and End-to-End Perspectives
Safety-aware metrics and losses for 3D detection improve critical error handling in autonomous vehicle perception across single-vehicle, cooperative, and end-to-end settings.
-
Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving
The paper introduces Hyper Diffusion Planner (HDP), a diffusion-based E2E AD framework that identifies insights on loss space, trajectory representation and data scaling, adds RL post-training, and reports 10x performance gains over 200 km of real-world testing across 6 scenarios.
-
Improving Backward Conformal Prediction via Non-Conformity Score Transformation
A step-function score transformation I_w = w·1{s≥w} reduces the estimated-coverage gap in Backward Conformal Prediction from about 4.2% to 1.1% on CIFAR-10, CIFAR-100, and Tiny-ImageNet.
-
LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
Reducing expert-student asymmetries in visibility, uncertainty, and route specification enables a new TransFuser v6 policy that reaches 95 DS on Bench2Drive and more than doubles prior scores on Longest6 v2 and Town13.
-
Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
Alpamayo-R1 introduces a VLA model with a Chain of Causation dataset and multi-stage SFT-plus-RL training that reports 12% better planning accuracy and 35% fewer close encounters versus trajectory-only baselines in driving tasks.
-
Automated Test Validators for Flaky Cyber-Physical System Simulators: Approach and Evaluation
Test validators generated via genetic programming using the Ochiai SBFL formula are more accurate and robust to flakiness than alternatives from Tarantula, Naish, decision trees, or rules, with 88.7% alignment to known requirements in CPS case studies.
-
EMMA: End-to-End Multimodal Model for Autonomous Driving
EMMA is an end-to-end multimodal LLM that converts camera data into trajectories, objects, and road graphs via text prompts and reports state-of-the-art motion planning on nuScenes plus competitive detection results on Waymo.
-
Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
-
Octo: An Open-Source Generalist Robot Policy
Octo is an open-source transformer-based generalist robot policy pretrained on 800k trajectories that serves as an effective initialization for finetuning across diverse robotic platforms.
-
3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
3D Diffuser Actor unifies diffusion policies with 3D scene features to set new state-of-the-art results on RLBench and CALVIN robot benchmarks.
-
GPT-Driver: Learning to Drive with GPT
GPT-3.5 is turned into an autonomous-vehicle motion planner by representing driving scenes and trajectories as language tokens and applying a prompting-reasoning-finetuning pipeline, with results shown on nuScenes.
-
Emergence of Exploratory Look-Around Behaviors through Active Observation Completion
An RL agent learns to actively explore by being rewarded for inferring unobserved scene parts after short glimpse sequences, with sidekick policy learning enabling generalization to other active perception tasks.
-
Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions
A grid-based convolutional architecture fuses semantic maps and 3D perceptions to model driving interactions and predict future agent states, evaluated on a new industry-grade dataset.
-
Human-like autonomy emerges from self-play and a pinch of human data
Self-play RL regularized with 30 minutes of human data produces driving policies that coordinate with humans, training in 15 hours on one GPU with 2500x less data than imitation learning.
-
ESAM++: Efficient Online 3D Perception on the Edge
ESAM++ introduces a 3D Sparse Feature Pyramid Network for efficient online 3D scene perception on edge devices, claiming competitive accuracy with up to 3x faster inference and 2x smaller model size than ESAM on four benchmarks.
-
Multi-Resolution End-to-End Deep Neural Network for Optimizing Latency-Accuracy Tradeoff in Autonomous Driving
Multi-resolution end-to-end CNN with per-resolution batch normalization and resolution retargeting improves safety metrics over fixed-resolution baselines in CARLA simulator tests.
-
RED: Adaptive Real-Time DAG Scheduling for Robotic Inference under Environmental Dynamics
RED is a deadline-aware DAG scheduler for robotic multi-task inference that adapts to environmental dynamics and supports MIMONet deployment.