Physics-informed Imitative Reinforcement Learning for Real-world Driving

• URL: http://arxiv.org/abs/2407.02508v3
• Date: Wed, 25 Jun 2025 14:06:21 GMT
• Title: Physics-informed Imitative Reinforcement Learning for Real-world Driving
• Authors: Hang Zhou, Yihao Qin, Dan Xu, Yiding Ji,
• Abstract summary: We propose a physics-informed imitative reinforcement learning (IRL) that is entirely data-driven.<n>Our approach exhibits 37.8% reduction in collision rate and 22.2% reduction in off-road rate compared to the baseline method.
• Score: 17.263297015508705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in imitative reinforcement learning (IRL) have considerably enhanced the ability of autonomous agents to assimilate expert demonstrations, leading to rapid skill acquisition in a range of demanding tasks. However, such learning-based agents face significant challenges when transferring knowledge to highly dynamic closed-loop environments. Their performance is significantly impacted by the conflicting optimization objectives of imitation learning (IL) and reinforcement learning (RL), sample inefficiency, and the complexity of uncovering the hidden world model and physics. To address this challenge, we propose a physics-informed IRL that is entirely data-driven. It leverages both expert demonstration data and exploratory data with a joint optimization objective, allowing the underlying physical principles of vehicle dynamics to emerge naturally from the training process. The performance is evaluated through empirical experiments and results exceed popular IL, RL and IRL algorithms in closed-loop settings on Waymax benchmark. Our approach exhibits 37.8% reduction in collision rate and 22.2% reduction in off-road rate compared to the baseline method.

Related papers

• From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning [59.88543114325153]
  We introduce the Seeing-to-Experiencing framework to scale the capability of navigation foundation models with reinforcement learning.<n>S2E combines the strengths of pre-training on videos and post-training through RL.<n>We establish a comprehensive end-to-end evaluation benchmark, NavBench-GS, built on photorealistic 3DGS reconstructions of real-world scenes.
  arXiv  Detail & Related papers  (2025-07-29T17:26:10Z)
• Cost-effective Reduced-Order Modeling via Bayesian Active Learning [12.256032958843065]
  We propose BayPOD-AL, an active learning framework based on an uncertainty-aware Bayesian proper decomposition (POD) approach.<n> Experimental results on predicting the temperature evolution over a rod demonstrate BayPOD-AL's effectiveness in suggesting the informative data.<n>We demonstrate BayPOD-AL's generalizability and efficiency by evaluating its performance on a dataset of higher temporal resolution than the training dataset.
  arXiv  Detail & Related papers  (2025-06-27T21:23:37Z)
• Enhancing Training Data Attribution with Representational Optimization [57.61977909113113]
  Training data attribution methods aim to measure how training data impacts a model's predictions.<n>We propose AirRep, a representation-based approach that closes this gap by learning task-specific and model-aligned representations explicitly for TDA.<n>AirRep introduces two key innovations: a trainable encoder tuned for attribution quality, and an attention-based pooling mechanism that enables accurate estimation of group-wise influence.
  arXiv  Detail & Related papers  (2025-05-24T05:17:53Z)
• A Knowledge-Informed Deep Learning Paradigm for Generalizable and Stability-Optimized Car-Following Models [15.34704164931383]
  Car-following models (CFMs) are fundamental to traffic flow analysis and autonomous driving.<n>We propose a Knowledge-Informed Deep Learning (KIDL) paradigm that distills the generalization capabilities of pre-trained Large Language Models (LLMs) into a lightweight and stability-aware neural architecture.<n>We evaluate KIDL on the real-world NGSIM and HighD datasets, comparing its performance with representative physics-based, data-driven, and hybrid CFMs.
  arXiv  Detail & Related papers  (2025-04-19T09:33:02Z)
• Learning to Drive by Imitating Surrounding Vehicles [0.6612847014373572]
  Imitation learning is a promising approach for training autonomous vehicles to navigate complex traffic environments. We propose a data augmentation strategy that enhances imitation learning by leveraging the observed trajectories of nearby vehicles. We evaluate our approach using the state-of-the-art learning-based planning method PLUTO on the nuPlan dataset and demonstrate that our augmentation method leads to improved performance in complex driving scenarios.
  arXiv  Detail & Related papers  (2025-03-08T00:40:47Z)
• TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning [61.33599727106222]
  TeLL-Drive is a hybrid framework that integrates a Teacher LLM to guide an attention-based Student DRL policy.<n>A self-attention mechanism then fuses these strategies with the DRL agent's exploration, accelerating policy convergence and boosting robustness.
  arXiv  Detail & Related papers  (2025-02-03T14:22:03Z)
• Continual Learning for Behavior-based Driver Identification [5.560336593474866]
  Behavior-based Driver Identification is an emerging technology that recognizes drivers based on their unique driving behaviors.<n>Most studies fail to account for the real-world challenges of deploying Deep Learning models within vehicles.<n>These challenges include operating under limited computational resources, adapting to new drivers, and changes in driving behavior over time.
  arXiv  Detail & Related papers  (2024-12-14T10:24:44Z)
• Variable-Speed Teaching-Playback as Real-World Data Augmentation for Imitation Learning [6.277546031193622]
  This paper proposes a novel method of data augmentation that is applicable to force control and preserves the advantages of real-world datasets. Experiment was conducted on bilateral control-based imitation learning using a method of imitation learning equipped with position-force control. Results showed a maximum 55% increase in success rate from a simple change in speed of real-world reactions.
  arXiv  Detail & Related papers  (2024-12-04T11:51:50Z)
• From Imitation to Exploration: End-to-end Autonomous Driving based on World Model [24.578178308010912]
  RAMBLE is an end-to-end world model-based RL method for driving decision-making. It can handle complex and dynamic traffic scenarios. It achieves state-of-the-art performance in route completion rate on the CARLA Leaderboard 1.0 and completes all 38 scenarios on the CARLA Leaderboard 2.0.
  arXiv  Detail & Related papers  (2024-10-03T06:45:59Z)
• 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)
• Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight [20.92646531472541]
  We propose a novel approach that combines the performance of Reinforcement Learning (RL) and the sample efficiency of Imitation Learning (IL) Our framework contains three phases teacher policy using RL with privileged state information distilling it into a student policy via IL, and adaptive fine-tuning via RL. Tests show our approach can not only learn in scenarios where RL from scratch fails but also outperforms existing IL methods in both robustness and performance.
  arXiv  Detail & Related papers  (2024-03-18T19:25:57Z)
• REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation [61.7171775202833]
  We introduce an efficient system for learning dexterous manipulation skills withReinforcement learning. The main idea of our approach is the integration of recent advances in sample-efficient RL and replay buffer bootstrapping. Our system completes the real-world training cycle by incorporating learned resets via an imitation-based pickup policy.
  arXiv  Detail & Related papers  (2023-09-06T19:05:31Z)
• Reinforcement Learning with Human Feedback for Realistic Traffic Simulation [53.85002640149283]
  Key element of effective simulation is the incorporation of realistic traffic models that align with human knowledge. This study identifies two main challenges: capturing the nuances of human preferences on realism and the unification of diverse traffic simulation models.
  arXiv  Detail & Related papers  (2023-09-01T19:29:53Z)
• End-to-end Lidar-Driven Reinforcement Learning for Autonomous Racing [0.0]
  Reinforcement Learning (RL) has emerged as a transformative approach in the domains of automation and robotics. This study develops and trains an RL agent to navigate a racing environment solely using feedforward raw lidar and velocity data. The agent's performance is then experimentally evaluated in a real-world racing scenario.
  arXiv  Detail & Related papers  (2023-09-01T07:03:05Z)
• Benchmarking Offline Reinforcement Learning on Real-Robot Hardware [35.29390454207064]
  Dexterous manipulation in particular remains an open problem in its general form. We propose a benchmark including a large collection of data for offline learning from a dexterous manipulation platform on two tasks. We evaluate prominent open-sourced offline reinforcement learning algorithms on the datasets and provide a reproducible experimental setup for offline reinforcement learning on real systems.
  arXiv  Detail & Related papers  (2023-07-28T17:29:49Z)
• Supervised Pretraining Can Learn In-Context Reinforcement Learning [96.62869749926415]
  In this paper, we study the in-context learning capabilities of transformers in decision-making problems. We introduce and study Decision-Pretrained Transformer (DPT), a supervised pretraining method where the transformer predicts an optimal action. We find that the pretrained transformer can be used to solve a range of RL problems in-context, exhibiting both exploration online and conservatism offline.
  arXiv  Detail & Related papers  (2023-06-26T17:58:50Z)
• Offline Robot Reinforcement Learning with Uncertainty-Guided Human Expert Sampling [11.751910133386254]
  Recent advances in batch (offline) reinforcement learning have shown promising results in learning from available offline data. We propose a novel approach that uses uncertainty estimation to trigger the injection of human demonstration data. Our experiments show that this approach is more sample efficient when compared to a naive way of combining expert data with data collected from a sub-optimal agent.
  arXiv  Detail & Related papers  (2022-12-16T01:41:59Z)
• Gradient-Based Trajectory Optimization With Learned Dynamics [80.41791191022139]
  We use machine learning techniques to learn a differentiable dynamics model of the system from data. We show that a neural network can model highly nonlinear behaviors accurately for large time horizons. In our hardware experiments, we demonstrate that our learned model can represent complex dynamics for both the Spot and Radio-controlled (RC) car.
  arXiv  Detail & Related papers  (2022-04-09T22:07:34Z)
• UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning [1.1339580074756188]
  Offline reinforcement learning (RL) provides a framework for learning decision-making from offline data. Self-driving vehicles (SDV) learn a policy, which potentially even outperforms the behavior in the sub-optimal data set. This motivates the use of model-based offline RL approaches, which leverage planning.
  arXiv  Detail & Related papers  (2021-11-22T10:37:52Z)
• Efficient Robotic Manipulation Through Offline-to-Online Reinforcement Learning and Goal-Aware State Information [5.604859261995801]
  We propose a unified offline-to-online RL framework that resolves the transition performance drop issue. We introduce goal-aware state information to the RL agent, which can greatly reduce task complexity and accelerate policy learning. Our framework achieves great training efficiency and performance compared with the state-of-the-art methods in multiple robotic manipulation tasks.
  arXiv  Detail & Related papers  (2021-10-21T05:34:25Z)
• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation [64.43440450794495]
  We conduct an extensive study of six offline learning algorithms for robot manipulation. Our study analyzes the most critical challenges when learning from offline human data. We highlight opportunities for learning from human datasets.
  arXiv  Detail & Related papers  (2021-08-06T20:48:30Z)
• PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning [84.30765628008207]
  We propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning. Our method outperforms the current state-of-the-art methods by a large margin on both benchmarks.
  arXiv  Detail & Related papers  (2021-06-08T07:37:37Z)
• DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation [57.358212277226315]
  In imitation learning from observation IfO, a learning agent seeks to imitate a demonstrating agent using only observations of the demonstrated behavior without access to the control signals generated by the demonstrator. Recent methods based on adversarial imitation learning have led to state-of-the-art performance on IfO problems, but they typically suffer from high sample complexity due to a reliance on data-inefficient, model-free reinforcement learning algorithms. This issue makes them impractical to deploy in real-world settings, where gathering samples can incur high costs in terms of time, energy, and risk. We propose a more data-efficient IfO algorithm
  arXiv  Detail & Related papers  (2021-03-31T23:46:32Z)
• AWAC: Accelerating Online Reinforcement Learning with Offline Datasets [84.94748183816547]
  We show that our method, advantage weighted actor critic (AWAC), enables rapid learning of skills with a combination of prior demonstration data and online experience. Our results show that incorporating prior data can reduce the time required to learn a range of robotic skills to practical time-scales.
  arXiv  Detail & Related papers  (2020-06-16T17:54:41Z)
• Multiplicative Controller Fusion: Leveraging Algorithmic Priors for Sample-efficient Reinforcement Learning and Safe Sim-To-Real Transfer [18.50206483493784]
  We present a novel approach to model-free reinforcement learning that can leverage existing sub-optimal solutions. During training, our gated fusion approach enables the prior to guide the initial stages of exploration. We show the efficacy of our Multiplicative Controller Fusion approach on the task of robot navigation.
  arXiv  Detail & Related papers  (2020-03-11T05:12:26Z)

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.