Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Gelu, Wang, Teng, Wu, Zhijie, Wu, Junliang, Li, Songyuan, Zhu, Xiangwei
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.15013
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914527003541504
author Liu, Gelu
Wang, Teng
Wu, Zhijie
Wu, Junliang
Li, Songyuan
Zhu, Xiangwei
author_facet Liu, Gelu
Wang, Teng
Wu, Zhijie
Wu, Junliang
Li, Songyuan
Zhu, Xiangwei
contents Autonomous bicycles offer a promising agile solution for urban mobility and last-mile logistics. However, conventional control strategies often struggle with underactuated nonlinear dynamics, suffering from sensitivity to model mismatches and limited adaptability to real-world uncertainties. To address this, we develop CycleRL, a comprehensive sim-to-real framework for robust autonomous bicycle control. Our approach establishes a direct perception-to-action mapping within the high-fidelity NVIDIA Isaac Sim environment, leveraging Proximal Policy Optimization (PPO) to optimize the control policy. The framework features a composite reward function tailored for concurrent balance maintenance, velocity tracking, and steering control. Crucially, systematic domain randomization is employed to reduce the reliance on precise system modeling, bridge the simulation-to-reality gap and facilitate direct transfer. In simulation, CycleRL achieves promising performance, including a 99.90% balance success rate, a heading tracking error of 1.15°, and a velocity tracking error of 0.18 m/s. These quantitative results, coupled with successful hardware deployment, validate DRL as an effective paradigm for autonomous bicycle control, offering superior adaptability over traditional methods. Video demonstrations are available at https://anony6f05.github.io/CycleRL/.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15013
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle Control
Liu, Gelu
Wang, Teng
Wu, Zhijie
Wu, Junliang
Li, Songyuan
Zhu, Xiangwei
Robotics
Autonomous bicycles offer a promising agile solution for urban mobility and last-mile logistics. However, conventional control strategies often struggle with underactuated nonlinear dynamics, suffering from sensitivity to model mismatches and limited adaptability to real-world uncertainties. To address this, we develop CycleRL, a comprehensive sim-to-real framework for robust autonomous bicycle control. Our approach establishes a direct perception-to-action mapping within the high-fidelity NVIDIA Isaac Sim environment, leveraging Proximal Policy Optimization (PPO) to optimize the control policy. The framework features a composite reward function tailored for concurrent balance maintenance, velocity tracking, and steering control. Crucially, systematic domain randomization is employed to reduce the reliance on precise system modeling, bridge the simulation-to-reality gap and facilitate direct transfer. In simulation, CycleRL achieves promising performance, including a 99.90% balance success rate, a heading tracking error of 1.15°, and a velocity tracking error of 0.18 m/s. These quantitative results, coupled with successful hardware deployment, validate DRL as an effective paradigm for autonomous bicycle control, offering superior adaptability over traditional methods. Video demonstrations are available at https://anony6f05.github.io/CycleRL/.
title CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle Control
topic Robotics
url https://arxiv.org/abs/2603.15013