LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts

TL;DR

LineRides introduces a line-guided reinforcement learning framework enabling a bicycle robot to perform diverse stunts from minimal user input without demonstrations, handling infeasible guidelines and temporal ambiguities.

Contribution

The paper presents a novel line-guided learning approach that allows a bicycle robot to learn stunt behaviors from spatial guidelines and sparse orientations without demonstrations.

Findings

Supports seamless transition between driving and stunts.

Enables five distinct stunts on command.

Handles physically infeasible guidelines effectively.

Abstract

Designing reward functions for agile robotic maneuvers in reinforcement learning remains difficult, and demonstration-based approaches often require reference motions that are unavailable for novel platforms or extreme stunts. We present LineRides, a line-guided learning framework that enables a custom bicycle robot to acquire diverse, commandable stunt behaviors from a user-provided spatial guideline and sparse key-orientations, without demonstrations or explicit timing. LineRides handles physically infeasible guidelines using a tracking margin that permits controlled deviation, resolves temporal ambiguity by measuring progress via traveled distance along the guideline, and disambiguates motion details through position- and sequence-based key-orientations. We evaluate LineRides on the Ultra Mobility Vehicle (UMV) and show that the policy trained with our methods supports seamless transitions between normal driving and stunt execution, enabling five distinct stunts on command: MiniHop, LargeHop, ThreePointTurn, Backflip, and DriftTurn.