PATH SMOOTHING STRATEGY BASED ON METAHEURISTIC ALGORITHMS FOR PROBABILISTIC FOAM

Resumo

The probabilistic Foam method (PFM) is a sampling-basedpath planning algorithm that ensures a feasible path boundedby a safe region. This method is ideal for assistive roboticsapplications, which demands a high level of safety, such asperforming a motion by an active exoskeleton. However,PFM generates non-smoothed paths, which results in nonanthropomorphicmovements. Thus, this paper presentssome optimization strategies based on metaheuristics to smooththe paths generated by PFM. Simulated experiments wereperformed using the Harmony Search Algorithm, and GeneticAlgorithm and they were applied to an exoskeleton toovercome an obstacle. Results show that our proposed approachis capable of smoothing paths for this application,which resulted in more anthropomorphic motions.