Learning to Drive in New Cities Without Human Demonstrations

• URL: http://arxiv.org/abs/2602.15891v1
• Date: Mon, 09 Feb 2026 00:31:20 GMT
• Title: Learning to Drive in New Cities Without Human Demonstrations
• Authors: Zilin Wang, Saeed Rahmani, Daphne Cornelisse, Bidipta Sarkar, Alexander David Goldie, Jakob Nicolaus Foerster, Shimon Whiteson,
• Abstract summary: We show that self-play multi-agent reinforcement learning can adapt a driving policy to a substantially different target city using only the map and meta-information.<n>We introduce NO data Map-based self-play for Autonomous Driving (NOMAD), which enables policy adaptation in a simulator constructed based on the target-city map.
• Score: 66.37858021482741
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While autonomous vehicles have achieved reliable performance within specific operating regions, their deployment to new cities remains costly and slow. A key bottleneck is the need to collect many human demonstration trajectories when adapting driving policies to new cities that differ from those seen in training in terms of road geometry, traffic rules, and interaction patterns. In this paper, we show that self-play multi-agent reinforcement learning can adapt a driving policy to a substantially different target city using only the map and meta-information, without requiring any human demonstrations from that city. We introduce NO data Map-based self-play for Autonomous Driving (NOMAD), which enables policy adaptation in a simulator constructed based on the target-city map. Using a simple reward function, NOMAD substantially improves both task success rate and trajectory realism in target cities, demonstrating an effective and scalable alternative to data-intensive city-transfer methods. Project Page: https://nomaddrive.github.io/

Related papers

• SPACeR: Self-Play Anchoring with Centralized Reference Models [50.55045557371374]
  Sim agent policies are realistic, human-like, fast, and scalable in multi-agent settings.<n>Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data.<n>We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a central reference policy.
  arXiv  Detail & Related papers  (2025-10-20T19:53:02Z)
• MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility [52.0930915607703]
  Recent advances in Robotics and Embodied AI make public urban spaces no longer exclusive to humans. Micromobility enabled by AI for short-distance travel in public urban spaces plays a crucial component in the future transportation system. We present MetaUrban, a compositional simulation platform for the AI-driven urban micromobility research.
  arXiv  Detail & Related papers  (2024-07-11T17:56:49Z)
• Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning [4.195122359359966]
  Large Language Models (LLMs) are trained on mass knowledge and proved to be equipped with astonishing inference abilities. In this work, we leverage LLMs to understand and profile the system dynamics by a prompt-based grounded action transformation.
  arXiv  Detail & Related papers  (2023-08-28T03:49:13Z)
• Model-Based Imitation Learning for Urban Driving [26.782783239210087]
  We present MILE: a Model-based Imitation LEarning approach to jointly learn a model of the world and a policy for autonomous driving. Our model is trained on an offline corpus of urban driving data, without any online interaction with the environment. Our approach is the first camera-only method that models static scene, dynamic scene, and ego-behaviour in an urban driving environment.
  arXiv  Detail & Related papers  (2022-10-14T11:59:46Z)
• GINK: Graph-based Interaction-aware Kinodynamic Planning via Reinforcement Learning for Autonomous Driving [10.782043595405831]
  There are many challenges in applying deep reinforcement learning (D) to autonomous driving in a structured environment such as an urban area. In this paper, we suggest a new framework that effectively combines graph-based intention representation and reinforcement learning for dynamic planning. The experiments show the state-of-the-art performance of our approach compared to the existing baselines.
  arXiv  Detail & Related papers  (2022-06-03T10:37:25Z)
• Learning Interactive Driving Policies via Data-driven Simulation [125.97811179463542]
  Data-driven simulators promise high data-efficiency for driving policy learning. Small underlying datasets often lack interesting and challenging edge cases for learning interactive driving. We propose a simulation method that uses in-painted ado vehicles for learning robust driving policies.
  arXiv  Detail & Related papers  (2021-11-23T20:14:02Z)
• Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients [7.58363583085932]
  We present an offline policy method for learning imitative policies for complex urban driving from a large corpus of real-world demonstrations. This is achieved by building a differentiable data-driven simulator on top of perception outputs and high-fidelity HD maps of the area. We train our proposed method on 100 hours of expert demonstrations on urban roads and show that it learns complex driving policies that generalize well and can perform a variety of driving maneuvers.
  arXiv  Detail & Related papers  (2021-09-27T20:19:18Z)
• Scalable Multiagent Driving Policies For Reducing Traffic Congestion [32.08636346620938]
  Past research has shown that in small scale mixed traffic scenarios with both AVs and human-driven vehicles, a small fraction of AVs executing a controlled multiagent driving policy can mitigate congestion. In this paper, we scale up existing approaches and develop new multiagent driving policies for AVs in scenarios with greater complexity.
  arXiv  Detail & Related papers  (2021-02-26T21:29:55Z)
• End-to-end Interpretable Neural Motion Planner [78.69295676456085]
  We propose a neural motion planner (NMP) for learning to drive autonomously in complex urban scenarios. We design a holistic model that takes as input raw LIDAR data and a HD map and produces interpretable intermediate representations. We demonstrate the effectiveness of our approach in real-world driving data captured in several cities in North America.
  arXiv  Detail & Related papers  (2021-01-17T14:16:12Z)
• TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors [74.67698916175614]
  We propose TrafficSim, a multi-agent behavior model for realistic traffic simulation. In particular, we leverage an implicit latent variable model to parameterize a joint actor policy. We show TrafficSim generates significantly more realistic and diverse traffic scenarios as compared to a diverse set of baselines.
  arXiv  Detail & Related papers  (2021-01-17T00:29:30Z)

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.