Scenario-Based Curriculum Generation for Multi-Agent Autonomous Driving

• URL: http://arxiv.org/abs/2403.17805v1
• Date: Tue, 26 Mar 2024 15:42:04 GMT
• Title: Scenario-Based Curriculum Generation for Multi-Agent Autonomous Driving
• Authors: Axel Brunnbauer, Luigi Berducci, Peter Priller, Dejan Nickovic, Radu Grosu,
• Abstract summary: We introduce MATS-Gym, a Multi-Agent Traffic Scenario framework to train agents in CARLA, a high-fidelity driving simulator. This paper unifies various existing approaches to traffic scenario description into a single training framework and demonstrates how it can be integrated with techniques from unsupervised environment design to automate the generation of adaptive auto-curricula.
• Score: 7.277126044624995
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The automated generation of diverse and complex training scenarios has been an important ingredient in many complex learning tasks. Especially in real-world application domains, such as autonomous driving, auto-curriculum generation is considered vital for obtaining robust and general policies. However, crafting traffic scenarios with multiple, heterogeneous agents is typically considered as a tedious and time-consuming task, especially in more complex simulation environments. In our work, we introduce MATS-Gym, a Multi-Agent Traffic Scenario framework to train agents in CARLA, a high-fidelity driving simulator. MATS-Gym is a multi-agent training framework for autonomous driving that uses partial scenario specifications to generate traffic scenarios with variable numbers of agents. This paper unifies various existing approaches to traffic scenario description into a single training framework and demonstrates how it can be integrated with techniques from unsupervised environment design to automate the generation of adaptive auto-curricula. The code is available at https://github.com/AutonomousDrivingExaminer/mats-gym.

Related papers

• Very Large-Scale Multi-Agent Simulation in AgentScope [112.98986800070581]
  We develop new features and components for AgentScope, a user-friendly multi-agent platform. We propose an actor-based distributed mechanism towards great scalability and high efficiency. We also provide a web-based interface for conveniently monitoring and managing a large number of agents.
  arXiv  Detail & Related papers  (2024-07-25T05:50:46Z)
• RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios [58.62407014256686]
  RealGen is a novel retrieval-based in-context learning framework for traffic scenario generation. RealGen synthesizes new scenarios by combining behaviors from multiple retrieved examples in a gradient-free way. This in-context learning framework endows versatile generative capabilities, including the ability to edit scenarios.
  arXiv  Detail & Related papers  (2023-12-19T23:11:06Z)
• Graph Convolutional Networks for Complex Traffic Scenario Classification [0.7919810878571297]
  A scenario-based testing approach can reduce the time required to obtain statistically significant evidence of the safety of Automated Driving Systems. Most methods on scenario classification do not work for complex scenarios with diverse environments. We propose a method for complex traffic scenario classification that is able to model the interaction of a vehicle with the environment.
  arXiv  Detail & Related papers  (2023-10-26T20:51:24Z)
• TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction [149.5716746789134]
  We show data-driven traffic simulation can be formulated as a world model. We present TrafficBots, a multi-agent policy built upon motion prediction and end-to-end driving. Experiments on the open motion dataset show TrafficBots can simulate realistic multi-agent behaviors.
  arXiv  Detail & Related papers  (2023-03-07T18:28:41Z)
• MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning [25.191567110519866]
  We develop a new driving simulation platform called MetaDrive for the study of reinforcement learning algorithms. Based on MetaDrive, we construct a variety of RL tasks and baselines in both single-agent and multi-agent settings.
  arXiv  Detail & Related papers  (2021-09-26T18:34:55Z)
• 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)
• Improving the Generalization of End-to-End Driving through Procedural Generation [35.41368856679809]
  We release an open-ended driving simulator called PGDrive to better evaluate and improve generalization of end-to-end driving. We validate that training with the increasing number of procedurally generated scenes significantly improves the generalization of the agent across scenarios of different traffic densities and road networks.
  arXiv  Detail & Related papers  (2020-12-26T06:23:14Z)
• SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving [96.50297622371457]
  Multi-agent interaction is a fundamental aspect of autonomous driving in the real world. Despite more than a decade of research and development, the problem of how to interact with diverse road users in diverse scenarios remains largely unsolved. We develop a dedicated simulation platform called SMARTS that generates diverse and competent driving interactions.
  arXiv  Detail & Related papers  (2020-10-19T18:26:10Z)
• MADRaS : Multi Agent Driving Simulator [15.451658979433667]
  We present MADRaS, an open-source multiagent driving simulator for use in the design and evaluation of motion planning algorithms for autonomous driving. MADRaS is built on TORCS, an open-source car-racing simulator.
  arXiv  Detail & Related papers  (2020-10-02T13:38:49Z)
• Multi-Agent Routing Value Iteration Network [88.38796921838203]
  We propose a graph neural network based model that is able to perform multi-agent routing based on learned value in a sparsely connected graph. We show that our model trained with only two agents on graphs with a maximum of 25 nodes can easily generalize to situations with more agents and/or nodes.
  arXiv  Detail & Related papers  (2020-07-09T22:16:45Z)

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.