This paper presents a novel trajectory planning method for collaborative robots, focusing on a risk-centric approach to enhance safety and performance. Drawing from risk management principles, encompassing factors such as operator safety, performance degradation, and internal robot- related issues, the proposed framework offers a comprehensive solution for offline trajectory planning and online reactive trajectory execution. The main contributions include developing and implementing a risk definition and assessment framework utilizing fuzzy inference systems, a mapping strategy leveraging fuzzy logic to correlate robot states with risk levels, and for- mulating a global measure for evaluating the overall risk. Ad- ditionally, the paper introduces a risk-driven motion planning algorithm aimed at minimizing trajectory risk. It also proposes a reactive trajectory adaptation method to respond dynamically to elevated risk levels during task execution. Validation through simulations and experiments with a 7 Degree of Freedom (DoF) robotic manipulator demonstrates the effectiveness of the proposed approach in generating risk-limited trajectories and adapting online to collision risk factors.
Plan it Safe: A Risk-Driven Motion Planning Framework for Collaborative Robots
Elena Stracca;Alessandro Palleschi;Lucia Pallottino;Paolo Salaris
In corso di stampa
Abstract
This paper presents a novel trajectory planning method for collaborative robots, focusing on a risk-centric approach to enhance safety and performance. Drawing from risk management principles, encompassing factors such as operator safety, performance degradation, and internal robot- related issues, the proposed framework offers a comprehensive solution for offline trajectory planning and online reactive trajectory execution. The main contributions include developing and implementing a risk definition and assessment framework utilizing fuzzy inference systems, a mapping strategy leveraging fuzzy logic to correlate robot states with risk levels, and for- mulating a global measure for evaluating the overall risk. Ad- ditionally, the paper introduces a risk-driven motion planning algorithm aimed at minimizing trajectory risk. It also proposes a reactive trajectory adaptation method to respond dynamically to elevated risk levels during task execution. Validation through simulations and experiments with a 7 Degree of Freedom (DoF) robotic manipulator demonstrates the effectiveness of the proposed approach in generating risk-limited trajectories and adapting online to collision risk factors.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.