Hamiltonian Dynamics Learning from Point Cloud Observations for Nonholonomic Mobile Robot Control

TL;DR

This paper presents a novel method for learning nonholonomic mobile robot dynamics directly from point-cloud data using Hamiltonian neural ODEs, enabling effective energy-based control without explicit state estimation.

Contribution

It introduces a point-cloud-based learning approach with Hamiltonian structure for improved data efficiency and control of nonholonomic robots, bypassing traditional state estimation.

Findings

Successful dynamics learning from point clouds on real robots

Effective energy-shaping control based on learned Hamiltonian models

Enhanced data efficiency compared to traditional methods

Abstract

Reliable autonomous navigation requires adapting the control policy of a mobile robot in response to dynamics changes in different operational conditions. Hand-designed dynamics models may struggle to capture model variations due to a limited set of parameters. Data-driven dynamics learning approaches offer higher model capacity and better generalization but require large amounts of state-labeled data. This paper develops an approach for learning robot dynamics directly from point-cloud observations, removing the need and associated errors of state estimation, while embedding Hamiltonian structure in the dynamics model to improve data efficiency. We design an observation-space loss that relates motion prediction from the dynamics model with motion prediction from point-cloud registration to train a Hamiltonian neural ordinary differential equation. The learned Hamiltonian model enables the design of an energy-shaping model-based tracking controller for rigid-body robots. We demonstrate dynamics learning and tracking control on a real nonholonomic wheeled robot.