Inverse Kinematics for Neuro-Robotic Grasping with Humanoid Embodied Agents

TL;DR

This paper presents CycleIK, a neuro-inspired inverse kinematics method enabling platform-independent, zero-shot motion planning for humanoid robots, demonstrated through grasping tasks with NICO and NICOL robots, integrated with a large language model-based embodied agent.

Contribution

It introduces CycleIK, a novel neural inverse kinematics approach that is platform-independent and effective for real-time motion planning in humanoid robots.

Findings

CycleIK outperforms or matches state-of-the-art methods in simulation.

Achieved 72-82% grasp success rate on NICO and NICOL robots.

Demonstrated verbal instruction-based control with a large language model.

Abstract

This paper introduces a novel zero-shot motion planning method that allows users to quickly design smooth robot motions in Cartesian space. A B\'ezier curve-based Cartesian plan is transformed into a joint space trajectory by our neuro-inspired inverse kinematics (IK) method CycleIK, for which we enable platform independence by scaling it to arbitrary robot designs. The motion planner is evaluated on the physical hardware of the two humanoid robots NICO and NICOL in a human-in-the-loop grasping scenario. Our method is deployed with an embodied agent that is a large language model (LLM) at its core. We generalize the embodied agent, that was introduced for NICOL, to also embody NICO. The agent can execute a discrete set of physical actions and allows the user to verbally instruct various different robots. We contribute a grasping primitive to its action space that allows for precise manipulation of household objects. The updated CycleIK method is compared to popular numerical IK solvers and state-of-the-art neural IK methods in simulation and is shown to be competitive with or outperform all evaluated methods when the algorithm runtime is very short. The grasping primitive is evaluated on both NICOL and NICO robots with a reported grasp success of 72% to 82% for each robot, respectively.