ContactNet: Online Multi-Contact Planning for Acyclic Legged Robot Locomotion

TL;DR

ContactNet is a neural network-based contact planner that rapidly ranks potential contact regions, enabling real-time multi-contact planning for legged robots in complex environments.

Contribution

The paper introduces ContactNet, a fast neural network-based contact planner that operates in approximately 1 ms, allowing concurrent execution with trajectory optimization in MPC for legged robots.

Findings

ContactNet achieves around 1 ms computation time.

It effectively plans contacts in complex environments.

Demonstrated success in simulation with Solo12 robot.

Abstract

In legged logomotion, online trajectory optimization techniques generally depend on heuristic-based contact planners in order to have low computation times and achieve high replanning frequencies. In this work, we propose ContactNet, a fast acyclic contact planner based on a multi-output regression neural network. ContactNet ranks discretized stepping regions, allowing to quickly choose the best feasible solution, even in complex environments. The low computation time, in the order of 1 ms, makes possible the execution of the contact planner concurrently with a trajectory optimizer in a Model Predictive Control (MPC) fashion. We demonstrate the effectiveness of the approach in simulation in different complex scenarios with the quadruped robot Solo12.