Roger Girgis

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving

Luke Rowe

Rodrigue De Schaetzen

Liam Paull

We present Poutine, a 3B-parameter vision-language model (VLM) tailored for end-to-end autonomous driving in long-tail driving scenarios. Po… (see more)utine 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 by fine-tuning Poutine-Base with Group Relative Policy Optimization (GRPO) using less than 500 preference-labeled frames from the Waymo validation set. We show that both VLT pretraining and RL fine-tuning are critical to attain strong driving performance in the long-tail. Poutine-Base achieves a rater-feedback score (RFS) of 8.12 on the validation set, nearly matching Waymo's expert ground-truth RFS. The final Poutine model achieves an RFS of 7.99 on the official Waymo test set, placing 1st in the 2025 Waymo Vision-Based End-to-End Driving Challenge by a significant margin. These results highlight the promise of scalable VLT pre-training and lightweight RL fine-tuning to enable robust and generalizable autonomy.

2025-06-12

ArXiv (preprint)

Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments

Felix Heide

2025-03-28

ArXiv (preprint)

Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments

Felix Heide

2025-01-01

CVPR (published)

CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning

Felix Heide

Evaluating autonomous vehicle stacks (AVs) in simulation typically involves replaying driving logs from real-world recorded traffic. However… (see more), agents replayed from offline data do not react to the actions of the AV, and their behaviour cannot be easily controlled to simulate counterfactual scenarios. Existing approaches have attempted to address these shortcomings by proposing methods that rely on heuristics or learned generative models of real-world data but these approaches either lack realism or necessitate costly iterative sampling procedures to control the generated behaviours. In this work, we take an alternative approach and propose CtRL-Sim, a method that leverages return-conditioned offline reinforcement learning within a physics-enhanced Nocturne simulator to efficiently generate reactive and controllable traffic agents. Specifically, we process real-world driving data through the Nocturne simulator to generate a diverse offline reinforcement learning dataset, annotated with various reward terms. With this dataset, we train a return-conditioned multi-agent behaviour model that allows for fine-grained manipulation of agent behaviours by modifying the desired returns for the various reward components. This capability enables the generation of a wide range of driving behaviours beyond the scope of the initial dataset, including those representing adversarial behaviours. We demonstrate that CtRL-Sim can efficiently generate diverse and realistic safety-critical scenarios while providing fine-grained control over agent behaviours. Further, we show that fine-tuning our model on simulated safety-critical scenarios generated by our model enhances this controllability.

2024-09-05

robot-learning.org/CoRL/2024/Conference (accepted)

openreview.net

CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning

Felix Heide

Evaluating autonomous vehicle stacks (AVs) in simulation typically involves replaying driving logs from real-world recorded traffic. However… (see more), agents replayed from offline data are not reactive and hard to intuitively control. Existing approaches address these challenges by proposing methods that rely on heuristics or generative models of real-world data but these approaches either lack realism or necessitate costly iterative sampling procedures to control the generated behaviours. In this work, we take an alternative approach and propose CtRL-Sim, a method that leverages return-conditioned offline reinforcement learning (RL) to efficiently generate reactive and controllable traffic agents. Specifically, we process real-world driving data through a physics-enhanced Nocturne simulator to generate a diverse offline RL dataset, annotated with various rewards. With this dataset, we train a return-conditioned multi-agent behaviour model that allows for fine-grained manipulation of agent behaviours by modifying the desired returns for the various reward components. This capability enables the generation of a wide range of driving behaviours beyond the scope of the initial dataset, including adversarial behaviours. We show that CtRL-Sim can generate realistic safety-critical scenarios while providing fine-grained control over agent behaviours.

2024-03-29

ArXiv (preprint)

Direct Behavior Specification via Constrained Reinforcement Learning

Julien Roy

Joshua Romoff

Pierre-Luc Bacon

Chris J Pal

The standard formulation of Reinforcement Learning lacks a practical way of specifying what are admissible and forbidden behaviors. Most oft… (see more)en, practitioners go about the task of behavior specification by manually engineering the reward function, a counter-intuitive process that requires several iterations and is prone to reward hacking by the agent. In this work, we argue that constrained RL, which has almost exclusively been used for safe RL, also has the potential to significantly reduce the amount of work spent for reward specification in applied RL projects. To this end, we propose to specify behavioral preferences in the CMDP framework and to use Lagrangian methods to automatically weigh each of these behavioral constraints. Specifically, we investigate how CMDPs can be adapted to solve goal-based tasks while adhering to several constraints simultaneously. We evaluate this framework on a set of continuous control tasks relevant to the application of Reinforcement Learning for NPC design in video games.

2022-06-28

Proceedings of the 39th International Conference on Machine Learning (published)

proceedings.mlr.press

Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion Prediction

Florian Golemo

Felipe Codevilla

Martin Weiss

Jim Aldon D'Souza

Samira Ebrahimi Kahou

Felix Heide

Robust multi-agent trajectory prediction is essential for the safe control of robotic systems. A major challenge is to efficiently learn a r… (see more)epresentation that approximates the true joint distribution of contextual, social, and temporal information to enable planning. We propose Latent Variable Sequential Set Transformers which are encoder-decoder architectures that generate scene-consistent multi-agent trajectories. We refer to these architectures as “AutoBots”. The encoder is a stack of interleaved temporal and social multi-head self-attention (MHSA) modules which alternately perform equivariant processing across the temporal and social dimensions. The decoder employs learnable seed parameters in combination with temporal and social MHSA modules allowing it to perform inference over the entire future scene in a single forward pass efficiently. AutoBots can produce either the trajectory of one ego-agent or a distribution over the future trajectories for all agents in the scene. For the single-agent prediction case, our model achieves top results on the global nuScenes vehicle motion prediction leaderboard, and produces strong results on the Argoverse vehicle prediction challenge. In the multi-agent setting, we evaluate on the synthetic partition of TrajNet++ dataset to showcase the model’s socially-consistent predictions. We also demonstrate our model on general sequences of sets and provide illustrative experiments modelling the sequential structure of the multiple strokes that make up symbols in the Omniglot data. A distinguishing feature of AutoBots is that all models are trainable on a single desktop GPU (1080 Ti) in under 48h.

2022-01-01

ICLR (published)

openreview.net

A Survey of Mobile Computing for the Visually Impaired

Martin Weiss

Margaux Luck

Joseph Paul Cohen

The number of visually impaired or blind (VIB) people in the world is estimated at several hundred million. Based on a series of interviews … (see more)with the VIB and developers of assistive technology, this paper provides a survey of machine-learning based mobile applications and identifies the most relevant applications. We discuss the functionality of these apps, how they align with the needs and requirements of the VIB users, and how they can be improved with techniques such as federated learning and model compression. As a result of this study we identify promising future directions of research in mobile perception, micro-navigation, and content-summarization.

2018-11-25

ArXiv (preprint)