ACCEPTED PAPERS

Autonomous mobile robots are increasingly performing tasks in our daily environments, e.g., cleaning offices or order picking in supermarkets. In such human-populated scenarios, it is crucial that these robots always navigate safely when performing their task. Existing state-of-the-art methods can ensure safety, but often require deterministic motions of humans and may lead to conservative behavior in dense human-populated environments. In this study, we investigate the use of control barrier functions (CBFs) and time-based rapidly exploring random trees (RRTs) to combine local safety with global task performance. We propose a trade-off function to balance safety and task progress in densely populated scenarios. Moreover, we ensure passive safety while accounting for the uncertain future motions of humans. We will validate our approach in simulation with different densities of humans, and on a real TIAGo robot. Preliminary results show that our algorithm improves performance in scenarios with tight spaces.

Collaborative robots are increasingly deployed alongside humans in factories, hospitals, schools, and other domains to enhance teamwork and efficiency. Systems that seamlessly integrate humans and robots into cohesive teams for coordinated and efficient task execution are needed, enabling studies on how robot collaboration policies affect team performance and teammates' perception of trust, fairness, and robot acceptance. Existing systems are limited, typically involving one human and one robot, and thus require more insight into broader team dynamics. Many rely on games or virtual simulations, neglecting the impact of a robot's physical presence. Most tasks are turn-based, hindering simultaneous execution and affecting efficiency. This paper introduces CoHRT (Collaboration System for Human-Robot Teamwork), which facilitates multi-human-robot teamwork through seamless collaboration, coordination, and communication. CoHRT utilizes a server-client-based architecture, a vision-based system to track task environments, and a simple interface for team action coordination. It allows for the design of tasks considering the human teammates' physical and mental workload and varied skill labels across the team members. We used CoHRT to design a collaborative block manipulation and jigsaw puzzle-solving task in a team of one Franka Panda robot and two humans. CoHRT is extensible to larger teams and diverse tasks. The system enables recording multi-modal collaboration data to develop adaptive collaboration policies for robots. We propose several research directions to utilize CoHRT in human-robot collaboration research and plan to open-source the system for the research community.

Robots continue to demonstrate significant benefits in assisting humans with repetitive and laborious tasks across various industries, so ensuring safe interactions becomes increasingly critical. This need is particularly pressing in agriculture, where dynamic environments and diverse tasks pose unique safety challenges. This paper introduces an advanced Safe Human-Robot Interaction framework specifically tailored for agricultural robots. The framework emphasizes safe collaboration and coexistence with both untrained and trained individuals, adhering to international safety standards and European directives. A central feature of our framework is a robust Finite State Machine that adeptly manages robot behavior across various operational states, ensuring adaptability to the various contexts of human interaction, such as collaboration or coexistence. To validate the framework, a set of criteria was implemented to infer the safety level, aiming to demonstrate improvements in safety, reliability, and operational efficiency. The intention of the safe human-robot interaction framework is to enhance the safety and functionality of agricultural robots, facilitating their broader adoption and more effective use in Agro-Food systems.

Unprecedented possibilities of quadruped robots have driven much research on the technical aspects of these robots. However, the social perception and acceptability of quadruped robots so far remain poorly understood. This work investigates whether the way we design quadruped robots' behaviors can affect people’s perception of safety in interactions with these robots. We designed and tested a dominant and submissive personality for the quadruped robot (Boston Dynamics Spot). These were tested in two different walking scenarios (head-on and crossing interactions) in a 2x2 within-subjects study. We collected both behavioral data and subjective reports on participants' perception of the interaction. The results highlight that participants perceived the submissive robot as safer compared to the dominant one. The behavioral dynamics of interactions did not change depending on the robot's appearance. Participants' previous in-person experience with the robot was associated with lower subjective safety ratings but did not correlate with the interaction dynamics. Our findings have implications for the design of quadruped robots and contribute to the body of knowledge on the social perception of non-humanoid robots. We call for a stronger standing of felt experiences in human-robot interaction research.

For robots to revolutionize our daily lives, they must be able to safely interact with humans. In this paper, we seek to learn a robot policy guaranteed to satisfy safety constraints for human-robot interactions. Typical RL algorithms only encourage constraint satisfaction through reward shaping. However, such soft constraints cannot offer the safety guarantees necessary for HRI. To address this gap, we propose POLICEd RL, a novel RL algorithm explicitly designed to enforce affine hard constraints in closed-loop with a black-box environment. Our key insight is to make the learned policy be affine around the unsafe set and to use this affine region as a repulsive buffer to prevent trajectories from violating the constraint. We prove that such policies guarantee constraint satisfaction. Our results demonstrate the capacity of POLICEd RL to enforce hard constraints in robotic tasks while significantly outperforming existing methods.