Autonomous overtaking trajectory optimization using reinforcement learning and opponent pose estimation

• URL: http://arxiv.org/abs/2603.27207v1
• Date: Sat, 28 Mar 2026 09:28:04 GMT
• Title: Autonomous overtaking trajectory optimization using reinforcement learning and opponent pose estimation
• Abstract summary: This paper presents a reinforcement learning mechanism for multi-agent autonomous racing environments.<n>The system uses LiDAR with a 2D detection algorithm and a depth camera with YOLO-based object detection to identify the vehicle to be overtaken.<n>The proposed algorithm successfully performs overtaking maneuvers in both simulation and real-world experiments.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vehicle overtaking is one of the most complex driving maneuvers for autonomous vehicles. To achieve optimal autonomous overtaking, driving systems rely on multiple sensors that enable safe trajectory optimization and overtaking efficiency. This paper presents a reinforcement learning mechanism for multi-agent autonomous racing environments, enabling overtaking trajectory optimization, based on LiDAR and depth image data. The developed reinforcement learning agent uses pre-generated raceline data and sensor inputs to compute the steering angle and linear velocity for optimal overtaking. The system uses LiDAR with a 2D detection algorithm and a depth camera with YOLO-based object detection to identify the vehicle to be overtaken and its pose. The LiDAR and the depth camera detection data are fused using a UKF for improved opponent pose estimation and trajectory optimization for overtaking in racing scenarios. The results show that the proposed algorithm successfully performs overtaking maneuvers in both simulation and real-world experiments, with pose estimation RMSE of (0.0816, 0.0531) m in (x, y).

Related papers

• SPARK: Low Latency Single-Camera 3D Pose Estimation for Autonomous Racing using Keypoints [5.912377792360711]
  We present SPARK, a single-camera pose-estimation algorithm for autonomous racing using keypoint detection.<n>It achieves long-range detection with high accuracy, exceeding the performance of state-of-the-art monocular camera detection algorithms.<n>We evaluate the performance of our approach on real-world autonomous racing data and compare it to state-of-the-art LiDAR and camera detection algorithms.
  arXiv  Detail & Related papers  (2026-06-16T13:45:11Z)
• Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing [73.88859384645264]
  Out-Of-Distribution (OOD) generalization to various racetracks utilizes Machine Learning (ML) to encode the mathematical relation between sensor data and vehicle actuation for end-to-end control.<n>This paper presents a DRL method that parameterizes nonlinear vehicle dynamics from the spectral distribution of depth measurements with a non-geometric, physics-informed reward, to infer vehicle time-optimal and overtaking racing controls with an Artificial Neural Network (ANN)<n>The policy outperforms human demonstrations by 12% in OOD tracks on proportionally scaled hardware, by maximizing the friction circle with tire dynamics that resemble an empirical Pacejka tire model.
  arXiv  Detail & Related papers  (2026-04-10T17:12:07Z)
• Data Augmentation Strategies for Robust Lane Marking Detection [5.140388424678906]
  This paper addresses the challenge of domain shift for side-mounted cameras used in lane-wheel monitoring by introducing a generative AI-based data enhancement pipeline.<n>The approach combines geometric perspective transformation, AI-driven inpainting, and vehicle body overlays to simulate deployment-specific viewpoints.<n>With the augmented data trained, both models show improved robustness to different conditions, including shadows.
  arXiv  Detail & Related papers  (2025-11-24T00:47:27Z)
• TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion [54.46664104437454]
  We propose TacoDepth, an efficient and accurate Radar-Camera depth estimation model with one-stage fusion.<n>Specifically, the graph-based Radar structure extractor and the pyramid-based Radar fusion module are designed.<n>Compared with the previous state-of-the-art approach, TacoDepth improves depth accuracy and processing speed by 12.8% and 91.8%.
  arXiv  Detail & Related papers  (2025-04-16T05:25:04Z)
• LiDAR-Based Vehicle Detection and Tracking for Autonomous Racing [0.8356765961526956]
  This paper presents the LiDAR-based perception algorithms deployed on Team PoliMOVE's autonomous racecar, which won multiple competitions in the Indy Autonomous Challenge series.<n> Experimental results demonstrate the algorithm's performance, robustness, computational efficiency, and suitability for autonomous racing applications.
  arXiv  Detail & Related papers  (2025-01-24T14:01:51Z)
• DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving [55.53171248839489]
  We propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving.<n>Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner.<n>Experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
  arXiv  Detail & Related papers  (2024-09-15T15:55:24Z)
• KAN-RCBEVDepth: A multi-modal fusion algorithm in object detection for autonomous driving [2.382388777981433]
  This paper introduces the KAN-RCBEVDepth method to enhance 3D object detection in autonomous driving. Our unique Bird's Eye View-based approach significantly improves detection accuracy and efficiency. The code will be released in urlhttps://www.laitiamo.com/laitiamo/RCBEVDepth-KAN.
  arXiv  Detail & Related papers  (2024-08-04T16:54:49Z)
• Traffic control using intelligent timing of traffic lights with reinforcement learning technique and real-time processing of surveillance camera images [0.0]
  The optimal timing of traffic lights is determined and applied according to several parameters. Deep learning methods were used in vehicle detection using the YOLOv9-C model. The use of transfer learning along with retraining the model on images of Iranian cars has increased the accuracy of the model.
  arXiv  Detail & Related papers  (2024-05-22T00:04:32Z)
• Safe Navigation: Training Autonomous Vehicles using Deep Reinforcement Learning in CARLA [0.0]
  The goal of this project is to train autonomous vehicles to make decisions to navigate in uncertain environments using deep reinforcement learning techniques. The simulator provides a realistic and urban environment for training and testing self-driving models.
  arXiv  Detail & Related papers  (2023-10-23T04:23:07Z)
• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• Tackling Real-World Autonomous Driving using Deep Reinforcement Learning [63.3756530844707]
  In this work, we propose a model-free Deep Reinforcement Learning Planner training a neural network that predicts acceleration and steering angle. In order to deploy the system on board the real self-driving car, we also develop a module represented by a tiny neural network.
  arXiv  Detail & Related papers  (2022-07-05T16:33:20Z)
• Efficient and Robust LiDAR-Based End-to-End Navigation [132.52661670308606]
  We present an efficient and robust LiDAR-based end-to-end navigation framework. We propose Fast-LiDARNet that is based on sparse convolution kernel optimization and hardware-aware model design. We then propose Hybrid Evidential Fusion that directly estimates the uncertainty of the prediction from only a single forward pass.
  arXiv  Detail & Related papers  (2021-05-20T17:52:37Z)
• Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images [58.287120077778205]
  We introduce a framework for analyzing robustness of the learning algorithm w.r.t varying quality in the image input for autonomous driving. Using the results of sensitivity analysis, we propose an algorithm to improve the overall performance of the task of "learning to steer"
  arXiv  Detail & Related papers  (2021-02-26T02:08:07Z)

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.