Multi-Objective Instantaneous Center of Rotation Optimization Using Sensors Feedback for Navigation in Self-Reconfigurable Pavement Sweeping Robot

Abstract

Pavement in outdoor settings is an unstructured environment with sharp corners, varying widths, and pedestrian activity that poses navigation challenges while cleaning for autonomous systems. In this work, an approach towards navigating without collision in constrained pavement spaces using the optimal instantaneous center of rotation (ICR) is demonstrated using an in-house developed omnidirectional reconfigurable robot named Panthera. The Panthera reconfigurable design results in varying footprints, supported by passive linear joints along the robot width, with locomotion and steering action using four wheels independent steering drive (4WISD). The robot kinematics and perception sensors system are discussed. Further, the ICR selection is carried out using multi-objective optimization, considering functions for steering, varying width, distance, and clearance to avoid a collision. The framework is incorporated in a local navigation planner and demonstrated experimentally in real pavement settings. The results with optimal selection of ICR in two dimensional space within the robot footprint successfully perform smooth navigation in the constraint space. It is experimentally highlighted with four different scenarios, i.e., constraint conditions encountered by a robot during navigation. Moreover, the formulation of optimal selection of ICR while avoiding collision is generic and can be used for other mobile robot architectures.