Robust Autonomy Emerges from Self-Play

• URL: http://arxiv.org/abs/2502.03349v1
• Date: Wed, 05 Feb 2025 16:41:05 GMT
• Title: Robust Autonomy Emerges from Self-Play
• Authors: Marco Cusumano-Towner, David Hafner, Alex Hertzberg, Brody Huval, Aleksei Petrenko, Eugene Vinitsky, Erik Wijmans, Taylor Killian, Stuart Bowers, Ozan Sener, Philipp Krähenbühl, Vladlen Koltun,
• Abstract summary: We show that robust and naturalistic driving emerges entirely from self-play in simulation at unprecedented scale. This is enabled by Gigaflow, a batched simulator that can synthesize and train on 42 years of subjective driving experience per hour.
• Score: 63.44745854476206
• License:
• Abstract: Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic driving emerges entirely from self-play in simulation at unprecedented scale -- 1.6~billion~km of driving. This is enabled by Gigaflow, a batched simulator that can synthesize and train on 42 years of subjective driving experience per hour on a single 8-GPU node. The resulting policy achieves state-of-the-art performance on three independent autonomous driving benchmarks. The policy outperforms the prior state of the art when tested on recorded real-world scenarios, amidst human drivers, without ever seeing human data during training. The policy is realistic when assessed against human references and achieves unprecedented robustness, averaging 17.5 years of continuous driving between incidents in simulation.

Related papers

• HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving [48.84595398410479]
  HUGSIM is a closed-loop, photo-realistic, and real-time simulator for evaluating autonomous driving algorithms. We tackle challenges of novel view synthesis in closed-loop scenarios, including viewpoint extrapolation and 360-degree vehicle rendering. HUGSIM offers a comprehensive benchmark across more than 70 sequences from KITTI-360, nuScenes, and PandaSet, along with over 400 varying scenarios.
  arXiv  Detail & Related papers  (2024-12-02T17:07:59Z)
• IGDrivSim: A Benchmark for the Imitation Gap in Autonomous Driving [35.64960921334498]
  textbfIGDrivSim is a benchmark built on top of the Waymax simulator. Our experiments show that this perception gap can hinder the learning of safe and effective driving behaviors. We show that combining imitation with reinforcement learning, using a simple penalty reward for prohibited behaviors, effectively mitigates these failures.
  arXiv  Detail & Related papers  (2024-11-07T12:28:52Z)
• Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data [56.49494318285391]
  We present Sim2Seg, a re-imagining of RCAN that crosses the visual reality gap for off-road autonomous driving. This is done by learning to translate randomized simulation images into simulated segmentation and depth maps. This allows us to train an end-to-end RL policy in simulation, and directly deploy in the real-world.
  arXiv  Detail & Related papers  (2022-10-25T17:50:36Z)
• Indy Autonomous Challenge -- Autonomous Race Cars at the Handling Limits [81.22616193933021]
  The team TUM Auton-omous Motorsports will participate in the Indy Autonomous Challenge in Octo-ber 2021. It will benchmark its self-driving software-stack by racing one out of ten autonomous Dallara AV-21 racecars at the Indianapolis Motor Speedway. It is an ideal testing ground for the development of autonomous driving algorithms capable of mastering the most challenging and rare situations.
  arXiv  Detail & Related papers  (2022-02-08T11:55:05Z)
• Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture [0.5735035463793008]
  We present an end-to-end control strategy for autonomous vehicles aimed at minimizing lap times in a time attack racing event. We also introduce AutoRACE Simulator, which was employed to simulate accurate vehicular and environmental dynamics.
  arXiv  Detail & Related papers  (2021-10-11T17:26:55Z)
• DriveGAN: Towards a Controllable High-Quality Neural Simulation [147.6822288981004]
  We introduce a novel high-quality neural simulator referred to as DriveGAN. DriveGAN achieves controllability by disentangling different components without supervision. We train DriveGAN on multiple datasets, including 160 hours of real-world driving data.
  arXiv  Detail & Related papers  (2021-04-30T15:30:05Z)
• Learning Accurate and Human-Like Driving using Semantic Maps and Attention [152.48143666881418]
  This paper investigates how end-to-end driving models can be improved to drive more accurately and human-like. We exploit semantic and visual maps from HERE Technologies and augment the existing Drive360 dataset with such. Our models are trained and evaluated on the Drive360 + HERE dataset, which features 60 hours and 3000 km of real-world driving data.
  arXiv  Detail & Related papers  (2020-07-10T22:25:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.