Proactive kinodynamic planning using the Extended Social Force Model and human motion prediction in urban environments

Abstract

Abstract-This paper presents a novel approach for robot navigation in crowded urban environments where people and objects are moving simultaneously while a robot is navigating. Avoiding moving obstacles at their corresponding precise moment motivates the use of a robotic planner satisfying both dynamic and nonholonomic constraints, also referred as kynodynamic constraints. We present a proactive navigation approach with respect its environment, in the sense that the robot calculates the reaction produced by its actions and provides the minimum impact on nearby pedestrians. As a consequence, the proposed planner integrates seamlessly planning and prediction and calculates a complete motion prediction of the scene for each robot propagation. Making use of the Extended Social Force Model (ESFM) allows an enormous simplification for both the prediction model and the planning system under differential constraints. Simulations and real experiments have been carried out to demonstrate the success of the proactive kinodynamic planner.

Learning the hidden human knowledge of UAV pilots when navigating in a cluttered environment for improving path planning

“…In this case, the repulsors ✓ rep are explicit in the obstacles and the attractor ✓ att is the force exerted by the goal (see also [9] in the framework of dynamical movement primitives, DMPs, or [10] in the framework of planning in a human-like manner). In the classic RRT, the repulsors ✓ rep are implicit in the obstacles to provide obstacle avoidance paths whereas the implicit attractor ✓ att is the force to reach a solution path toward the goal if it exists.…”

“…where w RiRj is a weight related to the importance of the relation between the repulsors R i and R j , computed as the number of considered n points, when obtainingd Rj ,TR i R j in (10).…”

Viewing Robot Navigation in Human Environment as a Cooperative Activity

“…The requirement for human motion prediction arises when we intend to design a robot navigation system that is socially acceptable [17]. Prediction of human trajectories independent of robot plans, however, does not alleviate the problem of purely reactive robot behavior [18]. For example, consider a corridor situation where a robot and a person could only cross each other in a side-by-side configuration ( fig.…”

Assessing the social criteria for human-robot collaborative navigation: A comparison of human-aware navigation planners

“…The robot navigation planners explained in [13] and [14] use the social force model to cope with uncertain human motions. In the extended social force model [15], [16] approach, every iteration of planning step uses the human prediction information which is dependent on the path calculated during the previous iteration. This is the second planner we are using for our comparison.…”