An official website of the United States government
This paper addresses the problem of dynamic allocation of robot resources to tasks with hierarchical representations and multiple types of execution constraints, with the goal of enabling single-robot multitasking capabilities. Although the vast majority of robot platforms are equipped with more than one sensor (cameras, lasers, sonars) and several actuators (wheels/legs, two arms), which would in principle allow the robot to concurrently work on multiple tasks, existing methods are limited to allocating robots in their entirety to only one task at a time. This approach employs only a subset of a robot's sensors and actuators, leaving other robot resources unused. Our aim is to enable a robot to make full use of its capabilities by having an individual robot multitask, distributing its sensors and actuators to multiple concurrent activities. We propose a new architectural framework based on Hierarchical Task Trees that supports multitasking through a new representation of robot behaviors that explicitly encodes the robot resources (sensors and actuators) and the environmental conditions needed for execution. This architecture was validated on a two-arm, mobile, PR2 humanoid robot, performing tasks with multiple types of execution constraints.
more »
« less
Human-Robot Collaboration and Dialogue for Fault Recovery on Hierarchical Tasks
Robotic systems typically follow a rigid approach to task execution, in which they perform the necessary steps in a specific order, but fail when having to cope with issues that arise during execution. We propose an approach that handles such cases through dialogue and human-robot collaboration. The proposed approach contributes a hierarchical control architecture that 1) autonomously detects and is cognizant of task execution failures, 2) initiates a dialogue with a human helper to obtain assistance, and 3) enables collaborative human-robot task execution through extended dialogue in order to 4) ensure robust execution of hierarchical tasks with complex constraints, such as sequential, non-ordering, and multiple paths of execution. The architecture ensures that the constraints are adhered to throughout the entire task execution, including during failures. The recovery of the architecture from issues during execution is validated by a human-robot team on a building task.
more »
« less
- Award ID(s):
- 1757929
- PAR ID:
- 10211190
- Date Published:
- Journal Name:
- International Conference on Social Robotics
- Volume:
- 12483
- Page Range / eLocation ID:
- 144-156
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)This paper presents a novel approach to robot task learning from language-based instructions, which focuses on increasing the complexity of task representations that can be taught through verbal instruction. The major proposed contribution is the development of a framework for directly mapping a complex verbal instruction to an executable task representation, from a single training experience. The method can handle the following types of complexities: 1) instructions that use conjunctions to convey complex execution constraints (such as alternative paths of execution, sequential or nonordering constraints, as well as hierarchical representations) and 2) instructions that use prepositions and multiple adjectives to specify action/object parameters relevant for the task. Specific algorithms have been developed for handling conjunctions, adjectives and prepositions as well as for translating the parsed instructions into parameterized executable task representations. The paper describes validation experiments with a PR2 humanoid robot learning new tasks from verbal instruction, as well as an additional range of utterances that can be parsed into executable controllers by the proposed system.more » « less
-
We consider multi-robot service scenarios, where tasks appear at any time and in any location of the working area. A solution to such a service task problem requires finding a suitable task assignment and a collision-free trajectory for each robot of a multi-robot team. In cluttered environments, such as indoor spaces with hallways, those two problems are tightly coupled. We propose a decentralized algorithm for simultaneously solving both problems, called Hierarchical Task Assignment and Path Finding (HTAPF). HTAPF extends a previous bio-inspired Multi-Robot Task Allocation (MRTA) framework [1]. In this work, task allocation is performed on an arbitrarily deep hierarchy of work areas and is tightly coupled with a fully distributed version of the priority-based planning paradigm [12], using only broadcast communication. Specifically, priorities are assigned implicitly by the order in which data is received from nearby robots. No token passing procedure or specific schedule is in place ensuring robust execution also in the presence of limited probabilistic communication and robot failures.more » « less
-
Task and motion planning represents a powerful set of hybrid planning methods that combine reasoning over discrete task domains and continuous motion generation. Traditional reasoning necessitates task domain models and enough information to ground actions to motion planning queries. Gaps in this knowledge often arise from sources like occlusion or imprecise modeling. This work generates task and motion plans that include actions cannot be fully grounded at planning time. During execution, such an action is handled by a provided human designed or learned closed-loop behavior. Execution combines offline planned motions and online behaviors till reaching the task goal. Failures of behaviors are fed back as constraints to find new plans. Forty real-robot trials and motivating demonstrations are performed to evaluate the proposed framework and compare against state-of-the-art. Results show faster execution time, less number of actions, and more success in problems where diverse gaps arise. The experiment data is shared for researchers to simulate these settings. The work shows promise in expanding the applicable class of realistic partially grounded problems that robots can address.more » « less
-
Disassembly currently is a labor-intensive process with limited automation. The main reason lies in the fact that disassembly usually has to address model variations from different brands, physical uncertainties resulting from component defects or damage during usage, and incomplete product information. To overcome these challenges and to automate the disassembly process through human-robot collaboration, this paper develops a disassembly sequence planner which distributes the disassembly task between human and robot in a human-robot collaborative setting. This sequence planner targets to address potential issues including distinctive products, variant orientations, and safety constraints of human operators. The proposed disassembly sequence planner identifies the locations and orientations of the to-be-disassembled items, determines the starting point, and generates the optimal dis-assembly sequence while complying with the disassembly rules and considering the safe constraints for human operators. This algorithm is validated by numerical and experimental tests: the robot can successfully locate and disassemble the pieces following the obtained optimal sequence, and complete the task via collaboration with the human operator without violating the constraints.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1007/978-3-030-62056-1_13
