Perceptive Locomotion through Nonlinear Model Predictive Control

This work is currently under review, a preprint is available:
www.researchga...
Title:
Perceptive Locomotion through Nonlinear Model Predictive Control
Authors:
Ruben Grandia, Fabian Jenelten, Shaohui Yang, Farbod Farshidian, and Marco Hutter
Abstract:
Dynamic locomotion in rough terrain requires accurate foot placement, collision avoidance, and planning of the underactuated dynamics of the system. Reliably optimizing for such motions and interactions in the presence of imperfect and often incomplete perceptive information is challenging. We present a complete perception, planning, and control pipeline, that can optimize motions for all degrees of freedom of the robot in real-time. To mitigate the numerical challenges posed by the terrain a sequence of convex inequality constraints is extracted as local approximations of foothold feasibility and embedded into an online model predictive controller. Steppability classification, plane segmentation, and a signed distance field are precomputed per elevation map to minimize the computational effort during the optimization. A combination of multiple-shooting, real-time iteration, and a filter-based line-search are used to solve the formulated problem reliably and at high rate. We validate the proposed method in scenarios with gaps, slopes, and stepping stones in simulation and experimentally on the ANYmal quadruped platform, resulting in state-of-the-art dynamic climbing.

[@123avneesh]

Isn't it interesting to see various systems come into play to create something so amazing!?
The lab's work is stunning to see. Excellent presentation.

[@aldoskyz8]

New video = really impressive, good job

[@rjung_ch]

Great work ETH!

[@paulcalhoun436]

Very well presented! I hope you continue to make such impressive progress in legged locomotion.

[@yanbo2u]

Indeed excellent work.

[@cardianlfan8827]

very impressive

[@santka3739]

Impressive 👌😉👍

[@gabrieleruscelli4450]

This work is astonishing, I will start a competition on this subject really soon, the purpose of the challenge will be to program the locomotion system from scratch, could you give me some suggestions on the papers to read?

[@santka3739]

Why does virtual way surface has an relative slow slope of stairs? 05:52 07:08
Can't believe that lidar wasn't recognize that they are 90° actually. It may lead to refuse overstep using narrow stairs, isn't it? 🤔

[@chunyangzhou9144]

The raw map was filtered to be smooth.

[@shinesei]

How is this different than spot?

[@jasonhackman5553]

Physically, maybe not much. But the video was showcasing the programming they did for path finding I believe.

[@sergius.boroda]

,👍