Admissible Abstractions for Near-optimal Task and Motion Planning

Vega-Brown, William; Roy, Nicholas

doi:10.24963/ijcai.2018/674

Cited by 25 publications

(27 citation statements)

References 5 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If we consider the original form of f , PETLON will be downgraded to a locally suboptimal algorithm: there can be shorter motion plan consistent with the task-level symbolic plan. It is acknowledged that there exist TMP algorithms that ensure local optimality using gradient-based optimization (Toussaint, 2015), and global optimality using abstractions (Vega-Brown & Roy, 2018). In contrast, we use off-the-shelf task planners from the literature of classical AI.…”

Section: Algorithmmentioning

confidence: 99%

The PETLON Algorithm to Plan Efficiently for Task-Level-Optimal Navigation

Zhang²,

Stone³

2020

jair

View full text Add to dashboard Cite

Intelligent mobile robots have recently become able to operate autonomously in large-scale indoor environments for extended periods of time. In this process, mobile robots need the capabilities of both task and motion planning. Task planning in such environments involves sequencing the robot’s high-level goals and subgoals, and typically requires reasoning about the locations of people, rooms, and objects in the environment, and their interactions to achieve a goal. One of the prerequisites for optimal task planning that is often overlooked is having an accurate estimate of the actual distance (or time) a robot needs to navigate from one location to another. State-of-the-art motion planning algorithms, though often computationally complex, are designed exactly for this purpose of finding routes through constrained spaces. In this article, we focus on integrating task and motion planning (TMP) to achieve task-level-optimal planning for robot navigation while maintaining manageable computational efficiency. To this end, we introduce TMP algorithm PETLON (Planning Efficiently for Task-Level-Optimal Navigation), including two configurations with different trade-offs over computational expenses between task and motion planning, for everyday service tasks using a mobile robot. Experiments have been conducted both in simulation and on a mobile robot using object delivery tasks in an indoor office environment. The key observation from the results is that PETLON is more efficient than a baseline approach that pre-computes motion costs of all possible navigation actions, while still producing plans that are optimal at the task level. We provide results with two different task planning paradigms in the implementation of PETLON, and offer TMP practitioners guidelines for the selection of task planners from an engineering perspective.

show abstract

Section: Algorithmmentioning

confidence: 99%

The PETLON Algorithm to Plan Efficiently for Task-Level-Optimal Navigation

Zhang²,

Stone³

2020

jair

View full text Add to dashboard Cite

show abstract

“…Most of the work has focused on hierarchical strategies, which typically commit to solutions from time-budgeted underlying motion planning subroutines, and heuristically [3], [39], [40] guide the search over actions in the task space [33], [34], [35]. An important aspect of manipulation task planning is the generation and evaluation of grasps that form these mode transitions.…”

Section: A Foundationsmentioning

confidence: 99%

Anytime Multi-arm Task and Motion Planning for Pick-and-Place of Individual Objects via Handoffs

Shome¹,

Bekris²

2019

2019 International Symposium on Multi-Robot and Multi-Agent Systems (MRS)

View full text Add to dashboard Cite

Automation applications are pushing the deployment of many high DoF manipulators in warehouse and manufacturing environments. This has motivated many efforts on optimizing manipulation tasks involving a single arm. Coordinating multiple arms for manipulation, however, introduces additional computational challenges arising from the increased DoFs, as well as the combinatorial increase in the available operations that many manipulators can perform, including handoffs between arms. The focus here is on the case of pickand-place tasks, which require a sequence of handoffs to be executed, so as to achieve computational efficiency, asymptotic optimality and practical anytime performance. The paper leverages recent advances in multi-robot motion planning for high DoF systems to propose a novel multi-modal extension of the dRRT * algorithm. The key insight is that, instead of naively solving a sequence of motion planning problems, it is computationally advantageous to directly explore the composite space of the integrated multi-arm task and motion planning problem, given input sets of possible pick and handoff configurations. Asymptotic optimality guarantees are possible by sampling additional picks and handoffs over time. The evaluation shows that the approach finds initial solutions fast and improves their quality over time. It also succeeds in finding solutions to harder problem instances relative to alternatives and can scale effectively as the number of robots increases.

show abstract

“…Substantial computational benefits [7] can reward planners that commit to decisions at a high level of abstraction [8], learning STRIPS-like symbols [9] or performing an efficient satisficing search [10]. In contrast, aiming for highly dynamic implementation in uncertain, unstructured settings, in [1] we introduced a provably correct architecture for completing assembly plans in 2D environments based on the integration of a vector-field reactive controller with a deliberative planner [11] that uses the angelic semantics [12] to guarantee hierarchical optimality. While high level deliberation has previously been coordinated with reactive planners on hardware-specialized physical systems [13], [14], harnessing the inherent relationship between mobility and manipulation [4], as well as the potential for dynamics to ameliorate kinematic task mismatches [15], can preserve platform generality and, thereby, its fitness for a greater diversity of tasks.…”

Section: B Prior Workmentioning

confidence: 99%

“…2. After a description of the offline deliberative planner, we proceed with the features of the online reactive module and the new, In the deliberative layer, a high-level planner [11] outputs a sequence of symbolic actions that are realized and executed sequentially using a reactive controller that issues unicycle velocity (u ku ) [1] and abstract gripper (g) commands (see Section III-B). The low-level gait layer uses the commands instructed by the reactive planner to call out appropriately parametrized joint-level feedback controllers (see [6] and Section III-C) for Minitaur.…”

Section: System Architecturementioning

confidence: 99%

“…In addition, the factored representation allows us to quickly construct graphs with an exponential number of vertices. However, the number of graph vertices is exponential in n. We can search for a near-optimal path through the graph in a reasonable amount of time using the angelic hierarchical A* algorithm [11], [12]. This algorithm interleaves the search over high-level decision, like which objects to grasp and in which order, and over lower-level details, like where objects should be placed, by using a hierarchy of abstract operators, which are implicitly-defined sets of plans that achieve a specified effect.…”

Section: A Deliberative Layermentioning

confidence: 99%

See 1 more Smart Citation

Sensor-Based Reactive Execution of Symbolic Rearrangement Plans by a Legged Mobile Manipulator

Vasilopoulos

Topping

Vega-Brown

et al. 2018

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

We demonstrate the physical rearrangement of wheeled stools in a moderately cluttered indoor environment by a quadrupedal robot that autonomously achieves a user's desired configuration. The robot's behaviors are planned and executed by a three layer hierarchical architecture consisting of: an offline symbolic task and motion planner; a reactive layer that tracks the reference output of the deliberative layer and avoids unanticipated obstacles sensed online; and a gait layer that realizes the abstract unicycle commands from the reactive module through appropriately coordinated joint level torque feedback loops. This work also extends prior formal results about the reactive layer to a broad class of nonconvex obstacles. Our design is verified both by formal proofs as well as empirical demonstration of various assembly tasks.

show abstract

Admissible Abstractions for Near-optimal Task and Motion Planning

Cited by 25 publications

References 5 publications

The PETLON Algorithm to Plan Efficiently for Task-Level-Optimal Navigation

The PETLON Algorithm to Plan Efficiently for Task-Level-Optimal Navigation

Anytime Multi-arm Task and Motion Planning for Pick-and-Place of Individual Objects via Handoffs

Sensor-Based Reactive Execution of Symbolic Rearrangement Plans by a Legged Mobile Manipulator

Contact Info

Product

Resources

About