Time optimal paths improve robotic search and retrieval tasks
Time-Optimal Ergodic Retrieval
Robotics
Summary
Finding and picking up objects quickly with robots can be tricky because the robot doesn’t know exactly when it will find the object or how long it will take to get back. This paper introduces a new way to plan the robot’s path so it can search efficiently and return to its base faster once the object is found. The authors treat the search detection as a random process and include the return trip in calculating the shortest overall mission time. Their tests show this method can reduce mission times by nearly 20%, especially when the return trip is long or complicated.
What this means in practice
- •For robotic system engineers: Design robot routes that minimize total time to find and retrieve objects including the return to base, especially in complex environments.
- •For warehouse automation teams: Optimize autonomous robot pick-and-return tasks in large storage areas to reduce cycle times and improve throughput.
Authors
Christian Sulana, Christian Hughes, Ian Abraham
Abstract
Retrieval tasks are a form of search task where a robot must explore, find an object, and return with it as quickly as possible. Recent work in ergodic control has demonstrated time-optimal path planning for search tasks where visitation is proportionally matched, within some tolerance, to a given target distribution. However, these planners minimize the duration of a full deterministic search, while retrieval missions end their search at an unknown point in the trajectory and must return to a given base. In this work, we propose a new formulation of the time-optimal ergodic search problem that models detection as a Poisson process and minimizes total mission time by including the return phase in the objective. Experimental results show that time-optimal ergodic retrieval (TOER) achieves up to $19\%$ shorter mission durations relative to ergodic baselines and that this advantage grows as the return phase becomes more costly. Simulation and hardware implementations validate TOER's compatibility with environments of non-convex geometry as well as both 2D and 3D search domains.