Real-time pursuit-evasion with humanoid robots

Abstract

We consider a pursuit-evasion problem between humanoids. In our scenario, the pursuer enters the safety area of the evader headed for collision, while the latter executes a fast evasive motion. Control schemes are designed for both the pursuer and the evader. They are structurally identical, although the objectives are different: the pursuer tries to align its direction of motion with the line-of-sight to the evader, whereas the evader tries to move in a direction orthogonal to the line-of-sight to the pursuer. At the core of the control scheme is a maneuver planning module which makes use of closedform expressions exclusively. This allows its use in a replanning framework, where each robot updates its motion plan upon completion of a step to account for the perceived motion of the other. Simulation and experimental results on NAO humanoids reveal an interesting asymptotic behavior which was predicted using unicycle as template models for trajectory generation.

MPC-based humanoid pursuit-evasion in the presence of obstacles

“…High-level velocity generation is based on the use of unicycles as template models. We summarize here the main points of this procedure and refer the reader to [12] for further details on pursuit-evasion with unicycles.…”

“…Under the assumption that the moving obstacle did not change its direction, we developed a method by which the humanoid could plan and execute in real time an evasion maneuver. In [12] we removed that assumption, and considered a worst-case scenario where the obstacle is actively chasing the humanoid. This led us to replace the moving obstacle with another humanoid, and to consider therefore a pursuit-evasion problem with humanoids.…”

“…In this work, we extend the work in [12] by considering the presence of obstacles in the environment where pursuitevasion takes places. This obviously complicates an already difficult problem, because each robot must perform its own main task and, at the same time, avoid nearby obstacles.…”

Humanoid gait generation for walk-to locomotion using single-stage MPC

“…As in [9], [10], we will adopt a unicycle as template model for high-level velocity generation. In particular, consider a unicycle placed at the origin of the current robot frame and aligned with the sagittal axis.…”

A behavior-based framework for safe deployment of humanoid robots

“…This evasion strategy is called move aside, as the humanoid moves (backwards) in a direction that is orthogonal to the object line of approach; other strategies are possible(Cognetti et al 2017).…”