Dream to Drive: Model-Based Vehicle Control Using Analytic World Models

• URL: http://arxiv.org/abs/2502.10012v1
• Date: Fri, 14 Feb 2025 08:46:49 GMT
• Title: Dream to Drive: Model-Based Vehicle Control Using Analytic World Models
• Authors: Asen Nachkov, Danda Pani Paudel, Jan-Nico Zaech, Davide Scaramuzza, Luc Van Gool,
• Abstract summary: We present three new task setups that allow us to learn next state predictors, optimal planners, and optimal inverse states. Unlike analytic policy (APG), which requires the gradient of the next simulator state with respect to the current actions, our proposed setups rely on the gradient of the next state with respect to the current state.
• Score: 67.20720048255362
• License:
• Abstract: Differentiable simulators have recently shown great promise for training autonomous vehicle controllers. Being able to backpropagate through them, they can be placed into an end-to-end training loop where their known dynamics turn into useful priors for the policy to learn, removing the typical black box assumption of the environment. So far, these systems have only been used to train policies. However, this is not the end of the story in terms of what they can offer. Here, for the first time, we use them to train world models. Specifically, we present three new task setups that allow us to learn next state predictors, optimal planners, and optimal inverse states. Unlike analytic policy gradients (APG), which requires the gradient of the next simulator state with respect to the current actions, our proposed setups rely on the gradient of the next state with respect to the current state. We call this approach Analytic World Models (AWMs) and showcase its applications, including how to use it for planning in the Waymax simulator. Apart from pushing the limits of what is possible with such simulators, we offer an improved training recipe that increases performance on the large-scale Waymo Open Motion dataset by up to 12% compared to baselines at essentially no additional cost.

Related papers

• Gradient-based Trajectory Optimization with Parallelized Differentiable Traffic Simulation [24.95575815501035]
  We present a parallelized differentiable traffic simulator based on the Intelligent Driver Model (IDM) Our vehicle simulator efficiently models vehicle motion, generating trajectories that can be supervised to fit real-world data. We show that we can use the simulator to filter noise in the input trajectories (trajectory filtering), reconstruct dense trajectories from sparse ones (trajectory reconstruction), and predict future trajectories.
  arXiv  Detail & Related papers  (2024-12-21T19:53:38Z)
• Autonomous Vehicle Controllers From End-to-End Differentiable Simulation [60.05963742334746]
  We propose a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers. Our proposed framework brings the differentiable simulator into an end-to-end training loop, where gradients of environment dynamics serve as a useful prior to help the agent learn a more grounded policy. We find significant improvements in performance and robustness to noise in the dynamics, as well as overall more intuitive human-like handling.
  arXiv  Detail & Related papers  (2024-09-12T11:50:06Z)
• Solving Motion Planning Tasks with a Scalable Generative Model [15.858076912795621]
  We present an efficient solution based on generative models which learns the dynamics of the driving scenes. Our innovative design allows the model to operate in both full-Autoregressive and partial-Autoregressive modes. We conclude that the proposed generative model may serve as a foundation for a variety of motion planning tasks.
  arXiv  Detail & Related papers  (2024-07-03T03:57:05Z)
• Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research [76.93956925360638]
  Waymax is a new data-driven simulator for autonomous driving in multi-agent scenes. It runs entirely on hardware accelerators such as TPUs/GPUs and supports in-graph simulation for training. We benchmark a suite of popular imitation and reinforcement learning algorithms with ablation studies on different design decisions.
  arXiv  Detail & Related papers  (2023-10-12T20:49:15Z)
• Constraint-based graph network simulator [9.462808515258464]
  We present a framework for constraint-based learned simulation. We implement our method using a graph neural network as the constraint function and gradient descent as the constraint solver. Our model achieves better or comparable performance to top learned simulators.
  arXiv  Detail & Related papers  (2021-12-16T19:15:11Z)
• Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation [98.51313127382937]
  We focus on the use of labels in the synthetic domain alone. Our approach introduces both a way to learn neural-invariant representations and a theoretically inspired view on how to sample the data from the simulator. We showcase our approach on the bird's-eye-view vehicle segmentation task with multi-sensor data.
  arXiv  Detail & Related papers  (2021-11-15T18:37:43Z)
• SimNet: Learning Reactive Self-driving Simulations from Real-world Observations [10.035169936164504]
  We present an end-to-end trainable machine learning system capable of realistically simulating driving experiences. This can be used for the verification of self-driving system performance without relying on expensive and time-consuming road testing.
  arXiv  Detail & Related papers  (2021-05-26T05:14:23Z)
• 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)
• Testing the Safety of Self-driving Vehicles by Simulating Perception and Prediction [88.0416857308144]
  We propose an alternative to sensor simulation, as sensor simulation is expensive and has large domain gaps. We directly simulate the outputs of the self-driving vehicle's perception and prediction system, enabling realistic motion planning testing.
  arXiv  Detail & Related papers  (2020-08-13T17:20:02Z)

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.