Multi-robot box-pushing in presence of measurement noise

Abstract

Abstract-Real-world multi-robot co-ordination problems, involving system (robot) design, control, and planning are often formulated in the settings of an optimization problem with a view to maximize system throughput/efficiency under the constraints on system resources. The paper aims at solving a multi-robot box-pushing problem in the presence of noisy sensory data using evolutionary algorithm. The process of co-ordination among multiple robots is characterized by a set of measurements and a set of estimators with a mathematical relationship between them (captured by the objective function). In the box-pushing problem by twin robots, the range data obtained by the robots at any instant of time are measurements, and the torque and/or force to be developed by the robots for a local movement of the box are estimators. We here use torques and forces developed by the robots to construct two objectives on minimization of energy consumed and time required for a local movement of the box in the presence of noisy sensory data. The box-pushing problem is solved using the proposed extended noisy non-dominated sorting bee colony (ENNSBC) algorithm to handle noise in the objective surfaces. Experiments undertaken in both simulation and realworld platforms reveal the superiority of the proposed ENNSBC to other competitor algorithms to solve the box-pushing problem with respect to the performance metrics defined in the literature.

A Comparison of Various Approaches to Reinforcement Learning Algorithms for Multi-robot Box Pushing

“…GA-based methods did not attempt to include obstacles in the environment and are not necessarily suitable for obstacle ridden environments. The noisy non-dominated sorting bee colony algorithm was applied to a box pushing problem with few obstacles and agents, and focused more on dealing with a noisy environment than the overall box pushing problem [6]. It can also be noted that the results of the Q-learning algorithm are affected by uncooperative actions in a way that is similar to noise.…”