Mirror-Descent Inverse Kinematics for Box-constrained Joint Space

by   Taisuke Kobayashi, et al.

This paper proposes a new Jacobian-based inverse kinematics (IK) explicitly considering box-constrained joint space. To control humanoid robots, the reference pose of end effector(s) is planned in task space, then mapped into the reference joints by IK. Due to the limited analytical solutions for IK, iterative numerical IK solvers based on Jacobian between task and joint spaces have become popular. However, the conventional Jacobian-based IK does not explicitly consider the joint constraints, and therefore, they usually clamp the obtained joints during iteration according to the constraints in practice. The problem in clamping operation has been pointed out that it causes numerical instability due to non-smoothed objective function. To alleviate the clamping problem, this study explicitly considers the joint constraints, especially the box constraints in this paper, inside the new IK solver. Specifically, instead of clamping, a mirror descent (MD) method with box-constrained real joint space and no-constrained mirror space is integrated with the conventional Jacobian-based IK methods, so-called MD-IK. In addition, to escape local optima nearly on the boundaries of constraints, a heuristic technique, called ϵ-clamping, is implemented as margin in software level. As a result, MD-IK achieved more stable and enough fast i) regulation on the random reference poses and ii) tracking to the random trajectories compared to the conventional IK solvers.


IKFlow: Generating Diverse Inverse Kinematics Solutions

Inverse kinematics - finding joint poses that reach a given Cartesian-sp...

Inverse Kinematics with Forward Dynamics Solvers for Sampled Motion Tracking

Tracking Cartesian trajectories with end-effectors is a fundamental task...

Physics-informed neural networks with hard constraints for inverse design

Inverse design arises in a variety of areas in engineering such as acous...

Safe Learning Reference Governor for Constrained Systems with Application to Fuel Truck Rollover Avoidance

This paper proposes a learning reference governor (LRG) approach to enfo...

Visibility-Constrained Control of Multirotor via Reference Governor

For safe vision-based control applications, perception-related constrain...

Motion Control of Redundant Robots with Generalised Inequality Constraints

We present an improved version of the Saturation in the Null Space (SNS)...

Robust Imitation via Mirror Descent Inverse Reinforcement Learning

Recently, adversarial imitation learning has shown a scalable reward acq...

Please sign up or login with your details

Forgot password? Click here to reset