A Safety-Aware Shared Autonomy Framework with BarrierIK Using Control Barrier Functions
Berk Guler, Kay Pompetzki, Yuanzheng Sun, Simon Manschitz, Jan Peters
AI summary
Problem
Linear blending in shared autonomy teleoperation often generates unsafe, collision-prone commands in cluttered environments because existing methods treat obstacle avoidance as a soft constraint rather than a hard guarantee.
Approach
BarrierIK intercepts blended human-autonomy commands and enforces control barrier function inequalities at the inverse kinematics layer to project them onto a mathematically safe set without compromising task objectives.
Key results
- Reduced violation time and increased minimum clearance in simulated cluttered scenes
- Maintained task tracking accuracy and motion smoothness across all tested baselines
- VR user study confirmed higher perceived safety, increased trust, and preference for the CBF-filtered system
- Delivered a scalable, differentiable CBF-constrained IK solver compatible with standard QP optimizers
Why it matters
It enables safer, constraint-guaranteed teleoperation in cluttered workspaces, directly benefiting human-robot collaboration in logistics, manufacturing, and remote operations.
Abstract
Shared autonomy blends operator intent with autonomous assistance. In cluttered environments, linear blend- ing can produce unsafe commands even when each source is individually collision-free. Many existing approaches model obstacle avoidance through potentials or cost terms, which only enforce safety as a soft constraint. In contrast, safety-critical control requires hard guarantees. We investigate the use of control barrier functions (CBFs) at the inverse kinematics (IK) layer of shared autonomy, targeting post-blend safety while preserving task performance. Our approach is evaluated in sim- ulation on representative cluttered environments and in a VR teleoperation study comparing pure teleoperation with shared autonomy. Across conditions, employing CBFs at the IK layer reduces violation time and increases minimum clearance while maintaining task performance. In the user study, participants reported higher perceived safety and trust, lower interference, and an overall preference for shared autonomy with our safety filter. Additional materials available at BarrierIK.