Exponential Fields Formulation for WMR Navigation

Abstract

Abstract. In this manuscript, an autonomous navigation algorithm for wheeled mobile robots (WMR) operating in dynamic environments (indoors or structured outdoors) is formulated. The planning scheme is of critical importance for autonomous navigational tasks in complex dynamic environments. In fast dynamic environments, path planning needs algorithms able to sense simultaneously a diversity of obstacles, and use such sensory information to improve real-time navigation control, while moving towards a desired goal destination. The framework tackles 4 issues: 1) Reformulation of the Social Force Model (SFM) adapted to WMR; 2) the cohesion of a general inertial scheme to represents motion in any coordinate system; 3) control of actuators rotational speed as a general model regardless kinematic restrictions; 4) assuming detection of features (obstacles/goals), adaptive numeric weights are formulated to affect navigational exponential components. Simulation and experimental outdoors results are presented to show the feasibility of the proposed framework.

Neural control and coordination of decentralized transportation robots

“…Other work presented partial exponential derivatives for local navigation in highly dynamic environments. 42 This work discloses an approach for distance coordination in terms of a relaxation time using sigmoidal partial derivatives with inputs from the ANN scheduler. The ANN task scheduler provides the state actions as outputs to the robot’s path planner.…”

Thermal Image Sensing Model for Robotic Planning and Search

“…We can mention the traditional inverse quadratic potential fields combined with state estimation [ 21 ], and approaches on time-varying potential fields [ 22 , 23 ]. In addition, other methods are the vector fields techniques using continuous nonlinear functions such as sigmoid [ 24 ], exponential [ 25 ], trajectories with harmonics [ 26 ], polynomial-type to reduce instability and [ 27 ], compound adapted trigonometric [ 28 ], and steering methods without depth data, but using visual angles [ 29 ].…”