Hyper-GoalNet: Goal-Conditioned Manipulation Policy Learning with HyperNetworks

TL;DR

Hyper-GoalNet introduces a hypernetwork-based approach for goal-conditioned robotic manipulation, generating task-specific policies that adapt to diverse goals and environments, with improved robustness and performance demonstrated through extensive experiments.

Contribution

The paper proposes Hyper-GoalNet, a novel framework that uses hypernetworks to generate goal-specific policy parameters, separating goal interpretation from state processing for better adaptability.

Findings

Significant performance improvements over state-of-the-art methods.

Enhanced robustness to environmental variability and sensor noise.

Effective generalization across diverse manipulation tasks.

Abstract

Goal-conditioned policy learning for robotic manipulation presents significant challenges in maintaining performance across diverse objectives and environments. We introduce Hyper-GoalNet, a framework that generates task-specific policy network parameters from goal specifications using hypernetworks. Unlike conventional methods that simply condition fixed networks on goal-state pairs, our approach separates goal interpretation from state processing -- the former determines network parameters while the latter applies these parameters to current observations. To enhance representation quality for effective policy generation, we implement two complementary constraints on the latent space: (1) a forward dynamics model that promotes state transition predictability, and (2) a distance-based constraint ensuring monotonic progression toward goal states. We evaluate our method on a comprehensive suite of manipulation tasks with varying environmental randomization. Results demonstrate significant performance improvements over state-of-the-art methods, particularly in high-variability conditions. Real-world robotic experiments further validate our method's robustness to sensor noise and physical uncertainties. Code is available at: https://github.com/wantingyao/hyper-goalnet.