Learning to Tune Pure Pursuit in Autonomous Racing: Joint Lookahead and Steering-Gain Control with PPO

2026-02-20 · Mohamed Elgouhary, Amr S. El-Wakeel arxiv

Pure Pursuit (PP) is widely used in autonomous racing for real-time path tracking due to its efficiency and geometric clarity, yet performance is highly sensitive to how key parameters-lookahead distance and steering gain-are chosen. Standard velocity-based schedules adjust these only approximately and often fail to transfer across tracks and speed profiles. We propose a reinforcement-learning (RL) approach that jointly chooses the lookahead Ld and a steering gain g online using Proximal Policy Optimization (PPO). The policy observes compact state features (speed and curvature taps) and outputs (Ld, g) at each control step. Trained in F1TENTH Gym and deployed in a ROS 2 stack, the policy drives PP directly (with light smoothing) and requires no per-map retuning. Across simulation and real-car tests, the proposed RL-PP controller that jointly selects (Ld, g) consistently outperforms fixed-lookahead PP, velocity-scheduled adaptive PP, and an RL lookahead-only variant, and it also exceeds a kinematic MPC raceline tracker under our evaluated settings in lap time, path-tracking accuracy, and steering smoothness, demonstrating that policy-guided parameter tuning can reliably improve classical geometry-based control.

📄 PDF Abstract BibTeX arXiv:2602.18386

Code (0)

등록된 구현이 없습니다.

Dynamic Lookahead Distance via Reinforcement Learning-Based Pure Pursuit for Autonomous Racing

2026-03-30 · Mohamed Elgouhary, Amr S. El-Wakeel arxiv

Pure Pursuit (PP) is a widely used path-tracking algorithm in autonomous vehicles due to its simplicity and real-time performance. However, its effectiveness is sensitive to the choice of lookahead distance: shorter valu…

Reinforcement Learning Autonomous Vehicles

RLPP: A Residual Method for Zero-Shot Real-World Autonomous Racing on Scaled Platforms

2025-01-28 · Edoardo Ghignone, Nicolas Baumann, Cheng Hu, Jonathan Wang 외

Autonomous racing presents a complex environment requiring robust controllers capable of making rapid decisions under dynamic conditions. While traditional controllers based on tire models are reliable, they often demand…

Autonomous Racing Reinforcement Learning (RL)

Partial End-to-end Reinforcement Learning for Robustness Against Modelling Error in Autonomous Racing

2023-12-11 · Andrew Murdoch, Johannes Cornelius Schoeman, Hendrik Willem Jordaan

In this paper, we address the issue of increasing the performance of reinforcement learning (RL) solutions for autonomous racing cars when navigating under conditions where practical vehicle modelling errors (commonly kn…

Autonomous Racing Imitation Learning Reinforcement Learning (RL)

A Modular Architecture Design for Autonomous Driving Racing in Controlled Environments

2025-12-03 · Brais Fontan-Costas, M. Diaz-Cacho, Ruben Fernandez-Boullon, Manuel Alonso-Carracedo 외 arxiv

This paper presents a modular autonomous driving architecture for Formula Student Driverless competition vehicles operating in closed-circuit environments. The perception module employs YOLOv11 for real-time traffic cone…

Stereo Depth Estimation Autonomous Driving

Iterative Semi-parametric Dynamics Model Learning For Autonomous Racing

2020-11-17 · Ignat Georgiev, Christoforos Chatzikomis, Timo Völkl, Joshua Smith 외

Accurately modeling robot dynamics is crucial to safe and efficient motion control. In this paper, we develop and apply an iterative learning semi-parametric model, with a neural network, to the task of autonomous racing…

Autonomous Racing