mlsanityData to 14 Oct 2026

CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle Control

arXiv 2603.15013 ↗First posted 16 Mar 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for autonomous driving and traffic

Abstract (arXiv)

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 1.15deg, 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://cpnt-lab.github.io/CycleRL/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 35 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

10 of 35 references.

References · 10

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  3. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  4. 2020Ultra Fast Structure-aware Deep Lane Detectioncited by 122
  5. 2019A Survey of Deep Learning Applications to Autonomous Vehicle Controlcited by 106
  6. 2020Bi-directional Domain Adaptation for Sim2Real Transfer of Embodied Navigation Agentscited by 35
  7. 2018Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Drivingcited by 18
  8. 2019Controlling an Autonomous Vehicle with Deep Reinforcement Learningcited by 13
  9. 2021Control of rough terrain vehicles using deep reinforcement learningcited by 6
  10. 2017Design and implementation of an adaptive critic-based neuro-fuzzy controller on an unmanned bicyclecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Path Following and Stabilisation of a Bicycle Model using a Reinforcement Learning Approach
  2. 2026Bicycle Acrobatics with Reinforcement Learning
  3. 2026MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving
  4. 2026Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation
  5. 2026LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts
  6. 2025Dynamics-Decoupled Trajectory Alignment for Sim-to-Real Transfer in Reinforcement Learning for Autonomous Driving
  7. 2023A Platform-Agnostic Deep Reinforcement Learning Framework for Effective Sim2Real Transfer towards Autonomous Driving
  8. 2026System Design of the Ultra Mobility Vehicle: A Driving, Balancing, and Jumping Bicycle Robot