An Intention-Aware Robust Safety Framework for Robot Teleoperation: Unifying Object Interaction and Obstacle Avoidance
Zhitao Gao, Fangyu Peng, Chen Chen, Yukui Zhang, Wenke Zhou, ChengAo Jiang, Rong Yan, Xiaowei Tang, Yu Wang
AI summary
Problem
Classical control barrier functions for teleoperation degrade under model uncertainties and external disturbances, while their fixed safety boundaries cannot adapt to dynamic operator intentions switching between object interaction and obstacle avoidance.
Approach
The authors propose a hierarchical framework that uses a virtual proxy to decouple safety control from physical robot dynamics, paired with an intention-aware adaptive CBF that detects and quantifies operator intent to dynamically adjust safety boundaries in real time.
Key results
- Hierarchical architecture isolates safety control from leader-follower synchronization
- Virtual proxy eliminates dependency on uncertain physical dynamics, enhancing robustness
- Intention-aware adaptive CBF dynamically expands or contracts safety boundaries based on operator intent
- Simulations and physical experiments reduce trajectory error by 37.8% and prevent task failure in crowded environments
Why it matters
Provides a robust, intent-adaptive safety layer that improves operational transparency and prevents collisions in complex telemanipulation tasks.
Abstract
Control barrier functions (CBFs) have proven to be effective for obstacle avoidance in robot teleoperation systems. However, for classical CBF, model uncertainties and external dis- turbances cansignificantlydegradetherobustnessofsafetycontrol. Moreover, the fixed safety boundary lacks adaptability to dynamic switching on operational intentions. To address these limitations, this paper presents a hierarchical safety teleoperation framework that separates the safety layer from the leader-follower teleopera- tionlayers.Onthisbasis,avirtualproxyisintroducedtoconstructa robust control-affine system decoupled from physical robot uncer- tainties and external disturbances. Building upon this, we propose an intention-aware adaptive control barrier function (IA-ACBF), which consists of two modules: intention detection and intention quantification. The intention detection module determines the op- erator’s transient intention, which belongs to object interaction or obstacle avoidance. The intention quantification module then maps this to the adaptation of safety boundaries. Finally, the per- formance of the proposed method is validated through simulations and experiments with the physical robot.