Adaptive Safety Filter for Refining Manipulator Control in Shared Human-Robot Spaces*

Robust control barrier function-based shared control for cognitive-physical human-robot collaboration

A robust coupled cognitive - physical shared-control framework for human - robot collaboration that guarantees forward invariance of the safe set and bounded closed-loop signals is proposed.

Safe and robust tube-based path-following for robot navigation

In this paper, we propose a new robust navigation framework for path following tasks in robots operating within unknown, cluttered environments. Our approach ensures reactive safety through obstacle avoidance and guaranteed convergence to a target path, while simultaneously mitigating the impact of unknown-but-bounded disturbances using a tube-based control strategy. The methodology integrates key aspects in the robot navigation: (i) a nominal Integrated Guidance and Control scheme for path-following employing Artificial Vector Fields guidance and Backstepping control; (ii) a smooth distance function that enables a continuous control law formulation for seamless obstacle avoidance; (iii) a unified control objective that balances collision avoidance with path-following; and (iv) an adaptive control component to provide robustness against external disturbances. We provide formal proofs of safety and stability using barrier functions and Lyapunov stability theory. The effectiveness of the proposed framework is validated through extensive numerical simulations.

Predictive Relative-Velocity Steering for Safe Robotic Manipulator Teleoperation in Dynamic Environments

Recent advances in teleoperation have enabled robotic manipulators to perform dexterous, human-arm-like motions. However, human operators may fail to avoid suddenly appearing obstacles promptly and effectively, particularly under network latency or limited attention, thereby creating safety risks. To address this issue, we propose a lightweight and modular framework for proactive collision avoidance, operating directly at the end-effector velocity-command level. After preprocessing the point cloud, the framework first predicts potential collisions based on time-to-collision (TTC) with integrated overshoot protection, and subsequently rotates the relative-velocity vector using Rodrigues'rotation formula. The deflection changes only the direction of the relative velocity while preserving its magnitude, thereby mitigating the deadlock problem commonly encountered by conventional artificial potential field (APF) methods. The prediction module compensates for point-cloud processing latency introduced by complex teleoperation pipelines, while the lightweight design enables the high-frequency control required for teleoperation. Simulations across diverse scenarios show that the proposed method achieves a higher end-effector collision avoidance rate than the baseline methods. Experiments on a physical robotic system further validate its collision-avoidance effectiveness.

Constrained Sampling MPC for Safe Contact-Rich Control: From Exploration to Precision via Hybrid Refinement

Formation-Preserving Control for Multi-Robot Systems: Experimental Validation

Artificial potential fields (APFs) are widely used for collision avoidance in robotic systems due to their simplicity and real-time performance. However, in cooperative environments, robots may undergo unnecessary displacements caused by repulsive forces from neighboring robots, even after reaching their target positions. This paper presents a formation-preserving control strategy that suppresses such unnecessary motion while retaining the standard APF behavior when robots are far from their desired positions. The stability of the proposed controller is proven through Lyapunov stability analysis. Furthermore, the theoretical analysis establishes local exponential stability and positive invariance of a neighborhood of the desired configuration. A formal proof of collision avoidance is also provided, ensuring that inter-robot safety constraints are preserved. The approach is validated through two simulations and two experiments: the first illustrates APF-induced fluctuations, whereas the second demonstrates that the proposed controller enables robots to maintain their desired target positions.

Human–Robot Shared Workspace Safety Enhancement Using Predictive Control

The concept of human-robot collaboration (HRC) is becoming a significant part of the contemporary industry as it aims at enhancing productivity, flexibility, and ergonomics. As opposed to conventional industrial robotics, where keeping physical distance between humans and robots guarantees safety, collaborative robots (cobots) work in the same work areas whereby humans and robots are in close and simultaneous contact. The above paradigm shift brings about huge safety issues because of unpredictable human behaviors, changing environments as well as balancing between safety and operation. Traditional reactive safety measures, e.g., emergency stops and fixed safety zones, tend to cause unjustifiable down-time and low productivity. In this paper, the paper builds up detailed research on improving the safety of the shared workspace of human and robot with predictive control methods the author emphasizes the idea of Model Predictive Control (MPC) and its variations. Predictive control provides the opportunity to predict upcoming human behaviors and environmental variations enabling the adjustment of the robot paths, its speed, and interaction forces in advance. This framework is suggested and combines human motion prediction, dynamic safety constraints, and optimal control formulation to realize safe, smooth, and efficient human-robot collaboration. An elaborate system architecture is created which includes sensor fusion, real time prediction models and constrained optimization. The mathematical formulations of the predictive control problem are offered, including cost functions and safety constraints that meet the international safety standards. The feasibility of the suggested solution is assessed by the means of simulation-based scenarios of the most common industrial processes, including cooperative assembly and handling of materials. Findings indicate that the involved safety measures, the lower probability of a collision, the ease of control of the behavior of a robot, as well as greater functionality in its tasks, are significantly better than those of the traditional reactive control schemes. The article is informative and gives a systematic guide to scholars and developers intending to implement predictive safety control in the collaborative robot system and the future research directions to adhere to robust, explainable, and standardized human-robot safety solutions.