Comparison of Distal Teacher Learning with Numerical and Analytical Methods to Solve Inverse Kinematics for Rigid-Body Mechanisms

02/29/2020
by   Tim von Oehsen, et al.
0

Several publications are concerned with learning inverse kinematics, however, their evaluation is often limited and none of the proposed methods is of practical relevance for rigid-body kinematics with a known forward model. We argue that for rigid-body kinematics one of the first proposed machine learning (ML) solutions to inverse kinematics – distal teaching (DT) – is actually good enough when combined with differentiable programming libraries and we provide an extensive evaluation and comparison to analytical and numerical solutions. In particular, we analyze solve rate, accuracy, sample efficiency and scalability. Further, we study how DT handles joint limits, singularities, unreachable poses, trajectories and provide a comparison of execution times. The three approaches are evaluated on three different rigid body mechanisms with varying complexity. With enough training data and relaxed precision requirements, DT has a better solve rate and is faster than state-of-the-art numerical solvers for a 15-DoF mechanism. DT is not affected by singularities while numerical solutions are vulnerable to them. In all other cases numerical solutions are usually better. Analytical solutions outperform the other approaches by far if they are available.

READ FULL TEXT

page 1

page 3

research
10/11/2020

Inverse Dynamics vs. Forward Dynamics in Direct Transcription Formulations for Trajectory Optimization

Benchmarks of state-of-the-art rigid-body dynamics libraries have report...
research
02/22/2022

Differentiable and Learnable Robot Models

Building differentiable simulations of physical processes has recently r...
research
10/16/2017

Learning Data-Efficient Rigid-Body Contact Models: Case Study of Planar Impact

In this paper we demonstrate the limitations of common rigid-body contac...
research
02/16/2021

Free surface shapes in rigid body rotation: Exact solutions, asymptotics and approximants

We analyze steady interface shapes in zero gravity in rotating right cir...
research
06/13/2022

A Versatile Pseudo-Rigid Body Modeling Method

A novel semi-analytical method is proposed to develop the pseudo-rigid-b...
research
01/21/2021

Differential Euler: Designing a Neural Network approximator to solve the Chaotic Three Body Problem

The three body problem is a special case of the n body problem where one...
research
12/17/2020

Scaling laws for the rigid-body response of masonry structures under blast loads

The response of masonry structures to explosions can be hardly investiga...

Please sign up or login with your details

Forgot password? Click here to reset