Intelligence is skill-acquisition efficiency, and the ARC benchmark measures human-like general fluid intelligence by testing abstraction and reasoning with minimal, innate-like priors.
hub
ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
abstract
Our goal is to train a policy for autonomous driving via imitation learning that is robust enough to drive a real vehicle. We find that standard behavior cloning is insufficient for handling complex driving scenarios, even when we leverage a perception system for preprocessing the input and a controller for executing the output on the car: 30 million examples are still not enough. We propose exposing the learner to synthesized data in the form of perturbations to the expert's driving, which creates interesting situations such as collisions and/or going off the road. Rather than purely imitating all data, we augment the imitation loss with additional losses that penalize undesirable events and encourage progress -- the perturbations then provide an important signal for these losses and lead to robustness of the learned model. We show that the ChauffeurNet model can handle complex situations in simulation, and present ablation experiments that emphasize the importance of each of our proposed changes and show that the model is responding to the appropriate causal factors. Finally, we demonstrate the model driving a car in the real world.
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
J-LAW introduces a coupled latent factor graph that jointly optimizes metric poses, latent states, and landmark embeddings to produce maps that are both metric and actionable for planning.
A diffusion-based autonomous driving planner that injects gradients from a spatio-temporal occupancy-and-route cost volume into late denoising steps improves closed-loop safety and progress across three benchmarks.
Double preconditioning (DoPr) improves downstream task performance in test-time feedback settings without consistent gains in validation loss.
Closed-loop on-policy training with a reactive goal-oriented scene decoder cuts collision rates by up to 79.5% in dense traffic compared to standard open-loop baselines.
CausalVAD applies sparse causal intervention to remove spurious correlations from end-to-end autonomous driving models, reporting state-of-the-art planning accuracy and robustness on nuScenes.
RoboNet is a multi-robot video dataset that enables pre-training of vision-based manipulation models which, after fine-tuning on a new robot, outperform robot-specific training that uses 4-20 times more data.
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.
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.
DriveVLM adds vision-language models with scene description, analysis, and hierarchical planning modules to autonomous driving, paired with a hybrid DriveVLM-Dual system tested on nuScenes and SUP-AD datasets and deployed on a production vehicle.
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.
Diffusion Forcing Planner applies heterogeneous joint diffusion with time-dependent noise and classifier-free guidance on history segments to generate stable, controllable motion plans for autonomous driving on nuPlan.
SafeAlign-VLA uses counterfactual safety pairing and anchor-based group relative policy optimization to incorporate negative data for safer VLA-based autonomous driving.
An instance-centric representation with local frames, relative positional encodings, and adaptive reward transformation in adversarial IRL yields scalable, accurate, and robust behavior models for multi-agent driving simulation.
citing papers explorer
-
On the Measure of Intelligence
Intelligence is skill-acquisition efficiency, and the ARC benchmark measures human-like general fluid intelligence by testing abstraction and reasoning with minimal, innate-like priors.
-
J-LAW: Joint Localization and Actionable World Modeling via Coupled Latent Factor Graphs
J-LAW introduces a coupled latent factor graph that jointly optimizes metric poses, latent states, and landmark embeddings to produce maps that are both metric and actionable for planning.
-
G2DP: Diffusion Planning with Spatio-Temporal Grid Guidance
A diffusion-based autonomous driving planner that injects gradients from a spatio-temporal occupancy-and-route cost volume into late denoising steps improves closed-loop safety and progress across three benchmarks.
-
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.
-
Goal-Oriented Reactive Simulation for Closed-Loop Trajectory Prediction
Closed-loop on-policy training with a reactive goal-oriented scene decoder cuts collision rates by up to 79.5% in dense traffic compared to standard open-loop baselines.
-
CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention
CausalVAD applies sparse causal intervention to remove spurious correlations from end-to-end autonomous driving models, reporting state-of-the-art planning accuracy and robustness on nuScenes.
-
RoboNet: Large-Scale Multi-Robot Learning
RoboNet is a multi-robot video dataset that enables pre-training of vision-based manipulation models which, after fine-tuning on a new robot, outperform robot-specific training that uses 4-20 times more data.
-
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.
-
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.
-
DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
DriveVLM adds vision-language models with scene description, analysis, and hierarchical planning modules to autonomous driving, paired with a hybrid DriveVLM-Dual system tested on nuScenes and SUP-AD datasets and deployed on a production vehicle.
-
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.
-
Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving
Diffusion Forcing Planner applies heterogeneous joint diffusion with time-dependent noise and classifier-free guidance on history segments to generate stable, controllable motion plans for autonomous driving on nuPlan.
-
SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Driving
SafeAlign-VLA uses counterfactual safety pairing and anchor-based group relative policy optimization to incorporate negative data for safer VLA-based autonomous driving.
-
Toward Efficient and Robust Behavior Models for Multi-Agent Driving Simulation
An instance-centric representation with local frames, relative positional encodings, and adaptive reward transformation in adversarial IRL yields scalable, accurate, and robust behavior models for multi-agent driving simulation.