Safe Autonomous Environmental Contact for Soft Robots using Control Barrier Functions

2025-04-20

AI Summary

Ensuring safe contact force control for soft robots operating in sensitive environments remains a critical challenge. Method: This paper proposes the first closed-loop feedback controller for soft robotic arms based on Control Barrier Functions (CBFs). By modeling nonlinear environmental deformation, it explicitly transforms force constraints into a safety set defined over end-effector pose, and enforces this constraint via real-time quadratic programming to supervise and correct nominal control inputs. Contribution/Results: We introduce a novel joint pose–contact-force logical specification and achieve the first formal safety verification of environmental contact forces for soft manipulators. Hardware experiments demonstrate that the framework strictly guarantees contact forces remain below prescribed thresholds for multi-segment pneumatic soft robotic arms, while ensuring safety, real-time performance, and formal verifiability—thereby advancing soft robot safety control from empirical design toward mathematically provable safety paradigms.

Technology Category

• Intelligent Robots: Manipulation
• Natural Language Processing: Safety and Robustness
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Authentication, authorization, and access control
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Robots built from soft materials will inherently apply lower environmental forces than their rigid counterparts, and therefore may be more suitable in sensitive settings with unintended contact. However, these robots' applied forces result from both their design and their control system in closed-loop, and therefore, ensuring bounds on these forces requires controller synthesis for safety as well. This article introduces the first feedback controller for a soft manipulator that formally meets a safety specification with respect to environmental contact. In our proof-of-concept setting, the robot's environment has known geometry and is deformable with a known elastic modulus. Our approach maps a bound on applied forces to a safe set of positions of the robot's tip via predicted deformations of the environment. Then, a quadratic program with Control Barrier Functions in its constraints is used to supervise a nominal feedback signal, verifiably maintaining the robot's tip within this safe set. Hardware experiments on a multi-segment soft pneumatic robot demonstrate that the proposed framework successfully constrains its environmental contact forces. This framework represents a fundamental shift in perspective on control and safety for soft robots, defining and implementing a formally verifiable logic specification on their pose and contact forces.

Problem

• Ensuring safe environmental contact for soft robots
• Developing feedback controller for force-bound compliance
• Verifying safety in soft robot pose and contact forces

Innovation

• Control Barrier Functions ensure soft robot safety
• Force bounds mapped to safe tip positions
• Quadratic program supervises nominal feedback signal