🤖 AI Summary
Robots navigating in dense pedestrian environments frequently encounter deadlock and collision issues. Method: This paper proposes a closed-loop joint optimization framework that unifies pedestrian motion prediction and robot trajectory planning. Its core innovation lies in the first-time integration of the ORCA pedestrian dynamics model as a hard constraint into a nonlinear model predictive control (MPC) formulation; the original bilevel optimization is reformulated into a single-level, tractable problem via Karush–Kuhn–Tucker (KKT) condition-based restructuring. This enables the robot to actively influence pedestrian behavior while strictly enforcing safety constraints. Results: Evaluated in both simulation and real-world indoor scenarios, the method achieves zero collisions and interactive navigation, significantly reduces pedestrian trajectory prediction error, and maintains real-time performance with per-step planning time under 100 ms.
📝 Abstract
Robots need to predict and react to human motions to navigate through a crowd without collisions. Many existing methods decouple prediction from planning, which does not account for the interaction between robot and human motions and can lead to the robot getting stuck. In this article, we propose safe and interactive crowd navigation (SICNav), a model predictive control (MPC) method that jointly solves for robot motion and predicted crowd motion in closed loop. We model each human in the crowd to be following an optimal reciprocal collision avoidance (ORCA) scheme and embed that model as a constraint in the robot's local planner, resulting in a bilevel nonlinear MPC optimization problem. We use a Karush–Kuhn–Tucker (KKT)-reformulation to cast the bilevel problem as a single level and use a nonlinear solver to optimize. Our MPC method can influence pedestrian motion while explicitly satisfying safety constraints in a single-robot multihuman environment. We analyze the performance of SICNav in two simulation environments and indoor experiments with a real robot to demonstrate safe robot motion that can influence the surrounding humans. We also validate the trajectory forecasting performance of ORCA on a human trajectory dataset.
