What does this research mean for the field?

A structured deep reinforcement learning framework that combines task-space via-point prediction with analytical redundancy resolution successfully generates energy-aware, dynamically balanced whole-body motions for high-DoF humanoid robots. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The aim is to develop a framework for optimizing humanoid robot trajectories using deep reinforcement learning while ensuring energy efficiency and dynamic balance.

June 21, 2026

Energy aware trajectory optimization using DRL in humanoid robot through via-point learning

Key Points

The aim is to develop a framework for optimizing humanoid robot trajectories using deep reinforcement learning while ensuring energy efficiency and dynamic balance.
Integrated task-space via-point learning with pseudo-inverse Jacobian for kinematic redundancy resolution.
Utilized a Soft Actor-Critic agent to predict task-space via-points for motion generation.
Validated on KONDO KHR-3HV with 24 independent trials per motion over different configurations.
Achieved energy-aware trajectories with zero ZMP violations in simulation.
Established a time-incentive reward system to effectively manage energy-time trade-offs.
Demonstrated preliminary transferability to a 23-DoFs platform in simulated environments.

Abstract

Abstract Learning whole-body motion for a 19-degrees-of-freedom (DoFs) humanoid robot using deep reinforcement learning (DRL) is challenging due to high kinematic redundancy, large joint-level search spaces, and the need to maintain dynamic balance. This paper proposes a structured DRL framework that integrates task-space via-point trajectory learning with a pseudo-inverse of Jacobian matrix for redundancy resolution (PJRR) method Instead of learning full joint trajectories, a Soft Actor–Critic (SAC) agent predicts a compact set of task-space via-points, which are converted into C2-continuous motions using composite cubic splines. Kinematic redundancy is resolved analytically through the PJRR, which operates separately from the learned policy and enforces a three-level task hierarchy: end-effector trajectory sub-task, hip trajectory sub-task, and posture regulation sub-task. The framework is validated on the KONDO KHR-3HV humanoid platform (1.3 kg, 19-DoFs) across four pick-and-place configurations, evaluated over N = 24 independent trials per motion. Energy-aware trajectories are generated with zero ZMP violations in simulation. A time-incentive reward formulation characterizes the energy–time trade-off, and a time-conditioned policy enables speed generalization at inference without retraining. Preliminary transferability to a scaled 23-DoFs platform is demonstrated in simulation.

Mark Helpful

Bookmark

Relay