Provable Indefinite-Horizon Real-Time Planning for Repetitive Tasks

Abstract

In many robotic manipulation scenarios, robots often have to perform highly-repetitive tasks in structured environments e.g. sorting mail in a mailroom or pick and place objects on a conveyor belt. In this work we are interested in settings where the tasks are similar, yet not identical (e.g., due to uncertain orientation of objects) and motion planning needs to be extremely fast. Preprocessing-based approaches prove to be very beneficial in these settings—they analyze the configuration-space offline to generate some auxiliary information which can then be used in the query phase to speedup planning times. Typically, the tighter the requirement is on query times the larger the memory footprint will be. In particular, for high-dimensional spaces, providing real-time planning capabilities is extremely challenging. While there are planners that guarantee real-time performance by limiting the planning horizon, we are not aware of general-purpose planners capable of doing it for indefinite horizon (i.e., planning to the goal). To this end, we propose a preprocessingbased method that provides provable bounds on the query time while incurring only a small amount of memory overhead in the query phase. We evaluate our method on a 7-DOF robot arm and show a speedup of over tenfold in query time when compared to the PRM algorithm.

Toward certifiable optimal motion planning for medical steerable needles

“…Motion primitives. Motion primitives, introduced by Frazzoli et al (2002), have been used in many motion planners (Islam et al, 2019(Islam et al, , 2020Lindemann and LaValle, 2006;Ljungqvist et al, 2017;Pivtoraiko and Kelly, 2011). In our setting, the motion primitives are a set of predefined kinematically feasible local motions.…”

Learning configurations of wires for real-time shape estimation and manipulation planning

“…Recently, a planning approach with provable constant-time guarantees (CTMP) has been introduced [1]- [3]. In all its variations, this method relies on a preprocessing phase where a library of intelligently computed paths is utilized during the online phase.…”

“…In all its variations, this method relies on a preprocessing phase where a library of intelligently computed paths is utilized during the online phase. In particular, [1] introduces a framework for decomposing a pre-defined region-of-interest (RoI) within a static environment into a set of sub-regions. By computing only one representative path per each sub-region, it enables an online planner to provably guarantee finding a plan to any state within the entire RoI within a user-defined (small) time bound.…”

“…It spans from residential to warehouse and factory environments, where tasks often involve a degree of environmental stability and repetition. Recently, a new concept of Constant-Time Motion Planning (CTMP) was introduced, with the aim of guaranteeing the ability to generate a motion plan within a (short) constant time in such environments [1]- [3]. CTMP has proven to be highly valuable in timecritical applications, such as manipulators catching incoming projectiles, operating on conveyor belts, and mail sorting in a mailroom.…”

“…Motivated by these challenges, we introduce an anytime variant of these algorithms. This variant employs a preprocessing phase, similar to [1] and [2], that enables the rapid generation of an initial solution -though potentially quite suboptimal -within a constant time constraint. Unlike previous approaches though, the algorithm progressively improves solution quality while adhering to the defined time budget, which can be determined by user-defined limits or based on previous execution times.…”