paper-with-me

Papers

Bicycle Acrobatics with Reinforcement Learning

2026-08-01 · Shamel Fahmi, Arianna Ilvonen, Samuel Zapolsky, Yu-Ming Chen, Ravi Boggavarapu, Paul Drews, Ashwin Khadke, Dean Molinaro, Kaiyu Zheng, Alfred Rizzi, Gabriel Nelson arxiv

Bicycle robots are fast and energy efficient, but their simple mechanical design and their underactuated and non-holonomic dynamics make highly agile maneuvers difficult to achieve. Here, we use Reinforcement Learning (RL) to enable a bicycle robot to learn and compose a diverse repertoire of dynamic acrobatic stunts. Using different RL formulations such as waypoint following, pose reaching, twist tracking, guided tracking, and motion imitation, the robot acquires autonomous single and multi-table forward and lateral jumps, steerable jumps, front flips, kip-ups, kip-downs, driving, wheelies, bunny hops, and three-point turns. To coordinate these behaviors, we introduce an orchestrator that transitions between policies using state-dependent triggers, enabling robust long-horizon acrobatic stunts. We validate the approach on the Ultra Mobility Vehicle (UMV), a custom bicycle robot, in simulation and hardware. The robot repeatedly traverses tables up to 1 m high, performs more than 15 consecutive autonomous jumps while following waypoints, handles previously unseen multi-table configurations, executes continuous repertoires of kipups, jumps, flips, kip-downs, over more than 20 consecutive trials, and performs more than 10 consecutive autonomous and steerable repertoires of wheelies, lateral jumps, and single-wheel jump downs. These results demonstrate that RL can endow bicycle robots with levels of agility previously associated primarily with legged platforms while preserving the speed and efficiency of wheeled locomotion, establishing a foundation for bicycle acrobatics.

📄 PDF Abstract BibTeX arXiv:2608.00880

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Dynamic Bicycle Dispatching of Dockless Public Bicycle-sharing Systems using Multi-objective Reinforcement Learning

2021-01-19 · Jianguo Chen, Kenli Li, Keqin Li, Philip S. Yu 외

As a new generation of Public Bicycle-sharing Systems (PBS), the dockless PBS (DL-PBS) is an important application of cyber-physical systems and intelligent transportation. How to use AI to provide efficient bicycle disp…

Multi-Objective Reinforcement LearningReinforcement Learning (RL)

Path Following and Stabilisation of a Bicycle Model using a Reinforcement Learning Approach

2024-07-24 · Sebastian Weyrer, Peter Manzl, A. L. Schwab, Johannes Gerstmayr

Over the years, complex control approaches have been developed to control the motion of a bicycle. Reinforcement Learning (RL), a branch of machine learning, promises easy deployment of so-called agents. Deployed agents …

Reinforcement Learning (RL)

Flip Stunts on Bicycle Robots using Iterative Motion Imitation

2026-03-30 · Jeonghwan Kim, Shamel Fahmi, Seungeun Rho, Sehoon Ha 외 arxiv

This work demonstrates a front-flip on bicycle robots via reinforcement learning, particularly by imitating reference motions that are infeasible and imperfect. To address this, we propose Iterative Motion Imitation(IMI)…

Reinforcement Learning

Dynamic Planning of Bicycle Stations in Dockless Public Bicycle-sharing System Using Gated Graph Neural Network

2021-01-19 · Jianguo Chen, Kenli Li, Keqin Li, Philip S. Yu 외

Benefiting from convenient cycling and flexible parking locations, the Dockless Public Bicycle-sharing (DL-PBS) network becomes increasingly popular in many countries. However, redundant and low-utility stations waste pu…

ClusteringGraph Neural NetworkManagement

Bikeability and the induced demand for cycling

2022-10-05 · Mogens Fosgerau, Miroslawa Lukawska, Mads Paulsen, Thomas Kjær Rasmussen

To what extent is the volume of urban bicycle traffic affected by the provision of bicycle infrastructure? In this study, we exploit a large dataset of observed bicycle trajectories in combination with a fine-grained rep…

counterfactual