K. Madhava Krishna PREM K. KALRA
Real-time motion planning in an unknown environment involves collision avoidance of static as well as moving agents. Strategies suitable for navigation in a stationary environment cannotbe translated as strategies per se for dynamic environments. In a purely stationary environment allthat the sensor can detect can only be a static object is assumed implicitly. In a mixed environmentsuch an assumption is no longer valid. For efficient collision avoidance identification of the attributeof the detected object as static or dynamic is probably inevitable. Presented here are two novelschemes for perceiving the presence of dynamic objects in the robot’s neighborhood. One of them,called the Model-Based Approach (MBA) detects motion by observing changes in the features of theenvironment represented on a map. The other CBA (cluster-based approach) partitions the contentsof the environment intoclusters representative of theobjects. Inspecting thecharacteristics of the par-titioned clusters reveals the presence of dynamic agents. The extracted dynamic objects are trackedin consequent samples of the environment through a straightforward nearest neighbor rule basedon the Euclidean metric. A distributed fuzzy controller avoids the tracked dynamic objects throughdirection and velocity control of the mobile robot. The collision avoidance scheme is extended toovercome multiple dynamic objects through a priority based averaging technique (PBA). Indicatingthe need for additional rules apart from the PBA to overcome conflicting decisions while tacklingmultiple dynamic objects can be considered as another contribution of this effort. The method hasbeen tested through simulations by navigating a sensor-based mobile robot amidst multiple dynamicobjects and its efficacy established