For a robot navigating in a human inhabited dynamic environment, the knowledge of how the robot’s movement can influence the trajectory of people around it can be very valuable. In this work we present a Human Motion Behaviour Aware Planner (HMBAP) which incorporates a Human Motion Behaviour Model (HMBM) in its planning stage to take advantage of this. HMBM is an obstacle avoidance model for people based on social forces which gives the robot an understanding of how people would react to its planned path. This information is useful for the robot to avoid imminent collisions with people in constricted spaces.
The planner uses the DWA to generate admissible trajectories, and then uses HMBM to estimate human motion behaviour for each of these trajectories. The predicted human trajectories are taken into account to evaluate the robot trajectories and choose the lowest cost one. We extend our method to incorporate the distinction of aware or unaware people. The method is fast and shows a human like behaviour of the robot in avoiding other humans around it.
Publication - Siddharth Oli, Bruno L’Esperance and Kamal Gupta, "Human Motion Behaviour Aware Planner (HMBAP) for Path Planning in Dynamic Human Environments" in press IEEE International Conference on Aadvanced Robotics 2013.
Experiments -
Simulations -