Socially Acceptable Bipedal Robot Navigation via Social Zonotope Network Model Predictive Control

This study addresses the challenge of social bipedal navigation in a dynamic, human-crowded environment, a research area largely underexplored in legged robot navigation. We present a zonotope-based framework that couples prediction and motion planning for a bipedal ego-agent to account for bidirectional influence with the surrounding pedestrians. This framework incorporates a Social Zonotope Network (SZN), a neural network that predicts future pedestrian reachable sets and plans future socially acceptable reachable set for the ego-agent. SZN generates the reachable sets as zonotopes for efficient reachability-based planning, collision checking, and online uncertainty parameterization. Locomotion-specific losses are added to the SZN training process to adhere to the dynamic limits of the bipedal robot that are not explicitly present in the human crowds data set. These loss functions enable the SZN to generate locomotion paths that are more dynamically feasible for improved tracking. SZN is integrated with a Model Predictive Controller (SZN-MPC) for footstep planning for our bipedal robot Digit. SZN-MPC solves for collision-free trajectory by optimizing through SZN’s gradients. Our results demonstrate the framework’s effectiveness in producing a socially acceptable path, with consistent locomotion velocity, and optimality. The SZN-MPC framework is validated with extensive simulations and hardware experiments. Note to Practitioners—This paper is motivated by the challenge of navigating bipedal robots through dynamic, human-crowded environments in a socially acceptable manner. Existing methods for social navigation often only address obstacle avoidance and are demonstrated on a robot with simple dynamics. This paper proposes the Social Zonotope Network (SZN), a novel neural network that couples pedestrian future trajectory prediction and robot motion planning to facilitate socially aware navigation for bipedal robots such as Digit, designed by Agility Robotics. The social behaviors are learned from real open-sourced pedestrian data using the SZN, which outputs the future predictions as reachable sets for each agent in the environment. The SZN is then integrated into a trajectory optimization problem that takes into account personal space preferences and bipedal robot capabilities to design trajectories that are both collision-free and socially acceptable. This work also highlights the computational efficiency of the SZN design that makes it suitable for real-time integration with motion planners. The framework is validated through extensive simulations and hardware experiments. From a practical standpoint, this research provides a framework that can be applied to bipedal robots to improve automation in human-populated environments such as hospitals, shopping centers, and airports. The framework’s ability to automatically adapt to surrounding human movement helps minimize disruptions and ensures that the robot’s presence is not a hindrance to the flow of human traffic. Future work will focus on outdoor deployment, which will require onboard perception capabilities to detect surrounding pedestrians.