Towards manipulation planning with temporal logic specifications

Abstract

Manipulation planning from high-level task specifications, even though highly desirable, is a challenging problem. The large dimensionality of manipulators and complexity of task specifications make the problem computationally intractable. This work introduces a manipulation planning framework with linear temporal logic (LTL) specifications. The use of LTL as the specification language allows the expression of rich and complex manipulation tasks. The framework deals with the state-explosion problem through a novel abstraction technique. Given a robotic system, a workspace consisting of obstacles, manipulable objects, and locations of interest, and a co-safe LTL specification over the objects and locations, the framework computes a motion plan to achieve the task through a synergistic multi-layered planning architecture. The power of the framework is demonstrated through case studies, in which the planner efficiently computes plans for complex tasks. The case studies also illustrate the ability of the framework in intelligently moving away objects that block desired executions without requiring backtracking.

Incremental Task and Motion Planning: A Constraint-Based Approach

“…In contrast, we motion plan anew each run, but efficiently update scene data structures to handle object interaction. The Synergistic Framework [65] and related methods [4,5,36] are similar to our proposed approach, but there are important differences in the underlying algorithms that suggest these methods may be complementary. The Synergistic Framework finds task plans through forward search, while we use constraint-based methods to efficiently generate task plans.…”

“…Our approach incorporates geometric information from failed motion planning attempts via incremental constraint updates, while the Synergistic Framework uses feedback between the task and motion planner to guide a weighted forward-search which may assist difficult motion planning domains. [36] also focuses on the manipulation domain; in comparison, our method provides both more flexible abstractions than [36]'s domain-specific task-state graph and significant performance improvements for the benchmarks in Sec. VII.…”

“…Previous work applied a variety of notations to the modeling of discrete robot tasks: temporal logics [3,36,47], structured and natural language [46,59], logical knowledge bases [25,75], the Planning Domain Definition Language (PDDL) [30,61,72], and context-free grammars [14,58,79]. Each notation provides advantages for certain domains or proprieties, e.g., safety properties are easily specified with temporal logics, action effects with PDDL, and hierarchies with grammars.…”

“…The typical algorithms for independent task planning [37,39,43,67] and motion planning [44,53] are fundamentally different. Consequently, most TMP methods [9,36,69,72] perform task planning and motion planning as separate, possibly interleaved, phases. We isolate and discuss the specific requirements for task planning, motion planning, and their interface in order to perform efficient and robust TMP.…”

“…VI). Finally, we validate our planner on a physical manipulator and show that it scales better with the number of objects and length of plan compared to the similar TMP method of [36] (see Sec. VII).…”