Learning Agile Tensile Perching for Aerial Robots from Demonstrations

2025-07-08

AI Summary

This work addresses the key challenge of enabling energy-efficient and agile tension-based perching of aerial robots on unstructured supports (e.g., tree branches, beams). The core difficulties lie in modeling cable dynamics—including slack-to-tension transitions and momentum transfer—and achieving precise cable wrapping control. To this end, we propose a demonstration-guided end-to-end reinforcement learning method. Our approach innovatively integrates both optimal and suboptimal human demonstrations and employs Soft Actor-Critic from Demonstrations (SACfD) for simulation-based pretraining and subsequent real-world transfer. Experimental results demonstrate that the learned policy achieves high-precision targeting of desired cable segments, smooth wrapping, and robust anchoring. It significantly improves perching success rate and驻留 stability in both simulation and physical experiments, while effectively extending operational endurance.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Perching on structures such as trees, beams, and ledges is essential for extending the endurance of aerial robots by enabling energy conservation in standby or observation modes. A tethered tensile perching mechanism offers a simple, adaptable solution that can be retrofitted to existing robots and accommodates a variety of structure sizes and shapes. However, tethered tensile perching introduces significant modelling challenges which require precise management of aerial robot dynamics, including the cases of tether slack & tension, and momentum transfer. Achieving smooth wrapping and secure anchoring by targeting a specific tether segment adds further complexity. In this work, we present a novel trajectory framework for tethered tensile perching, utilizing reinforcement learning (RL) through the Soft Actor-Critic from Demonstrations (SACfD) algorithm. By incorporating both optimal and suboptimal demonstrations, our approach enhances training efficiency and responsiveness, achieving precise control over position and velocity. This framework enables the aerial robot to accurately target specific tether segments, facilitating reliable wrapping and secure anchoring. We validate our framework through extensive simulation and real-world experiments, and demonstrate effectiveness in achieving agile and reliable trajectory generation for tensile perching.

Problem

• Modeling challenges in tethered tensile perching dynamics
• Precise control for smooth wrapping and anchoring
• Efficient trajectory generation for diverse perching structures

Innovation

• Reinforcement learning for tensile perching control
• Soft Actor-Critic from Demonstrations algorithm
• Optimal and suboptimal demonstrations integration