Alternative Paths Planner (APP) for Provably Fixed-time Manipulation Planning in Semi-structured Environments

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.…”

“…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. This concept was subsequently expanded to encompass static environments featuring dynamic goal objects [2], as well as semi-static environments [3]. However, these methods usually generate solutions within a few milliseconds and do not exploit the entire time budget available to them during an online phase.…”

“…Our approach to obtaining an initial solution within a constant-time framework is built upon a preprocessing phase that enables efficient online computations. Similarly to [1]- [3], during the offline phase, we assume access to a planner P and a predefined home state s home (the framework can also be extended to support a finite set of home configurations). A straightforward approach might involve computing and storing paths from s home to all states in G and all feasible paths between any s i , s j ∈ G pairs.…”

“…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.…”

“…For example, consider the assembly cell illustrated in Fig. 1, where three robotic arms continuously pick and place objects in a semi-static environment [3]. In such an environment, while the general settings remain constant, the manipulated objects can move within their designated regions.…”