Leveraging Neural Network Gradients within Trajectory Optimization for Proactive Human-Robot Interactions
This work provides a method for robots to achieve more seamless and proactive interactions with humans by better integrating advanced human behavior prediction into their motion planning, which is crucial for safe and efficient human-robot collaboration.
This paper addresses the challenge of integrating complex neural network-based human behavior models into robot motion planning for human-robot interaction. The authors developed a framework that uses gradient information from data-driven human trajectory prediction models within a gradient-based trajectory optimization problem. This approach resulted in safer and more efficient robot navigation in multi-agent scenarios with up to ten pedestrians, demonstrating proactive behaviors.
To achieve seamless human-robot interactions, robots need to intimately reason about complex interaction dynamics and future human behaviors within their motion planning process. However, there is a disconnect between state-of-the-art neural network-based human behavior models and robot motion planners -- either the behavior models are limited in their consideration of downstream planning or a simplified behavior model is used to ensure tractability of the planning problem. In this work, we present a framework that fuses together the interpretability and flexibility of trajectory optimization (TO) with the predictive power of state-of-the-art human trajectory prediction models. In particular, we leverage gradient information from data-driven prediction models to explicitly reason about human-robot interaction dynamics within a gradient-based TO problem. We demonstrate the efficacy of our approach in a multi-agent scenario whereby a robot is required to safely and efficiently navigate through a crowd of up to ten pedestrians. We compare against a variety of planning methods, and show that by explicitly accounting for interaction dynamics within the planner, our method offers safer and more efficient behaviors, even yielding proactive and nuanced behaviors such as waiting for a pedestrian to pass before moving.