This paper focuses on requirements for effective human robot collaboration in interactive navigation scenarios. We designed several use-cases where humans and robot had to move in the same environment that resemble canonical path-crossing situations. These use-cases include open as well as constrained spaces. Three different state-of-the-art human-aware navigation planners were used for planning the robot paths during all selected use-cases. We compare results of simulation experiments with these human-aware planners in terms of quality of generated trajectories together with discussion on capabilities and limitations of the planners. The results show that the human-robot collaborative planner [1] performs better in everyday path-crossing configurations. This suggests that the criteria used by the human-robot collaborative planner (safety, time-to-collision, directional-costs) are possible good measures for designing acceptable human-aware navigation planners. Consequently, we analyze the effects of these social criteria and draw perspectives on future evolution of human-aware navigation planning methods.

Robot navigation in human environments has been in the eyes of researchers for the last few years. Robots operating under these circumstances have to take human awareness into consideration for safety and acceptance reasons. Nonetheless, navigation have been often treated as going towards a goal point or avoiding people, without considering the robot engaging a person or a group of people in order to interact with them. This paper presents two navigation approaches based on the use of inverse reinforcement learning (IRL) from exemplar situations. This allow us to implement two path planners that take into account social norms for navigation towards isolated people. For the first planner, we learn an appropriate way to approach a person in an open area without static obstacles, this information is used to generate robot's path plan. As for the second planner, we learn the weights of a linear combination of continuous functions that we use to generate a costmap for the approach-behavior. This costmap is then combined with others, e.g. a costmap with higher cost around obstacles, and finally a path is generated with Dijkstra's algorithm.

A common approach to social distancing in robot navigation are spatial cost functions around humans that cause the robot to prefer paths that do not come too close to humans. However, in unpredictably dynamic scenarios, following such paths may produce robot behavior that appears confused. The concept of directional costs in cost functions [9] is supposed to alleviate this problem without incurring the problem of combinatorial explosions using temporal planning. With directional cost functions, a robot attempts to solve spatial conflicts by adjusting the velocity instead of the path, where possible. To complement results from simulations, in this paper we describe a user study we conducted with a PR2 robot and human participants to evaluate the new cost function type. The study shows that the real robot behavior is similar to the observations in simulation, and that participants rate the robot behavior less confusing with the adapted cost model. The study also shows other important behavior cues that can influence motion legibility.