We present AVOCADO (AdaptiVe Optimal Collision Avoidance Driven by Opinion), a novel navigation approach to address holonomic robot collision avoidance when the degree of cooperation of the other agents in the environment is unknown [1]. AVOCADO departs from a Velocity Obstacle’s formulation akin to the Optimal Reciprocal Collision Avoidance method. However, instead of assuming reciprocity, AVOCADO poses an adaptive control problem that aims at adapting in real-time to the cooperation degree of other robots and agents. Adaptation is achieved through a novel nonlinear opinion dynamics design that relies solely on sensor observations. As a by-product, based on the nonlinear opinion dynamics, we propose a novel method to avoid the deadlocks under geometrical symmetries among robots and agents. Extensive numerical simulations show that AVOCADO surpasses existing geometrical, learning and planning-based approaches in mixed cooperative/non-cooperative navigation environments in terms of success rate, time to goal and computational time. In addition, we conduct multiple real experiments that verify that AVOCADO is able to avoid collisions in environments crowded with other robots and humans.
We reformulate geometrical obstacle avoidance methods based on reciprocity and cooperation to handle more general scenarios, where the degree of cooperation of the encountered agents is not known a priori. This reformulation adds generality and enables to capture a wider variety of behaviors.
To enable fast and flexible adaptation to unknown degree of cooperation, we design an adaptive law based on nonlinear opinion dynamics. Supported by theoretical findings, the adaptive law relies solely on onboard measurements to appropriately estimate the degree of cooperation of the encountered agent.
Different simulated examples show that our method achieves fast, flexible adaptation to a wide variety of scenarios, mixing cooperative and non-cooperative agents, always in the absence of communication with other robots or agents. The maneuvers are smooth, inexpensive to compute, and guarantee collision avoidance.
Experiments with robots and humans demonstrate that our method is easy to apply in real settings, achieving effective collision avoidance in compact, crowded scenarios.
References:
[1] Martinez-Baselga, D., Sebastián, E., Montijano, E., Riazuelo, L., Sagüés, C., & Montano, L., "AVOCADO: Adaptive Optimal Collision Avoidance driven by Opinion". under review at IEEE Transactions on Robotics, 2024.