An official website of the United States government
Robots deployed in many real-world settings need to be able to acquire new skills and solve new tasks over time. Prior works on planning with skills often make assumptions on the structure of skills and tasks, such as subgoal skills, shared skill implementations, or task-specific plan skeletons, which limit adaptation to new skills and tasks. By contrast, we propose doing task planning by jointly searching in the space of parameterized skills using high-level skill effect models learned in simulation. We use an iterative training procedure to efficiently generate relevant data to train such models. Our approach allows flexible skill parameterizations and task specifications to facilitate lifelong learning in general-purpose domains. Experiments demonstrate the ability of our planner to integrate new skills in a lifelong manner, finding new task strategies with lower costs in both train and test tasks. We additionally show that our method can transfer to the real world without further fine-tuning.
more »
« less
Efficient task planning using abstract skills and dynamic road map matching
Task planning is the problem of finding a discrete sequence of actions to achieve a goal. Unfortunately, task planning in robotic domains is computationally challenging. To address this, in our prior work, we explained how knowledge from a successful task solution can be cached for later use, as an “abstract skill.” Such a skill is represented as a trace of states (“road map”) in an abstract space and can be matched with new tasks on-demand. This paper explains how one can use a library of abstract skills, derived from past planning experience, to reduce the computational cost of solving new task planning problems. As we explain, matching a skill to a task allows us to decompose it into independent sub-tasks, which can be quickly solved in parallel. This can be done automatically and dynamically during planning. We begin by formulating this problem of “planning with skills” as a constraint satisfaction problem. We then provide a hierarchical solution algorithm, which integrates with any standard task planner. Finally, we experimentally demonstrate the computational benefits of the approach for reach-avoid tasks.
more »
« less
- Award ID(s):
- 1830549
- PAR ID:
- 10483230
- Editor(s):
- Billard, A; Asfour, T; Khatib, O.
- Publisher / Repository:
- Springer
- Date Published:
- Journal Name:
- International Symposium on Robotics Research ISRR 2022
- ISBN:
- 978-3-031-25554-0
- Format(s):
- Medium: X
- Location:
- Geneva, Switzerland
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Robotic task planning is computationally challenging. To reduce planning cost and support life-long operation, we must leverage prior planning experience. To this end, we address the problem of extracting reusable and generalizable abstract skills from successful plan executions. In previous work, we introduced a supporting framework, allowing us, theoretically, to extract an abstract skill from a single execution and later automatically adapt it and reuse it in new domains. We also proved that, given a library of such skills, we can significantly reduce the planning effort for new problems. Nevertheless, until now, abstract-skill extraction could only be performed manually. In this paper, we finally close the automation loop and explain how abstract skills can be practically and automatically extracted. We start by analyzing the desired qualities of an abstract skill and formulate skill extraction as an optimization problem. We then develop two extraction algorithms, based on the novel concept of abstraction-critical state detection. As we show experimentally, the approach is independent of any planning domain.more » « less
-
One promising approach towards effective robot decision making in complex, long-horizon tasks is to sequence together parameterized skills. We consider a setting where a robot is initially equipped with (1) a library of parameterized skills, (2) an AI planner for sequencing together the skills given a goal, and (3) a very general prior distribution for selecting skill parameters. Once deployed, the robot should rapidly and autonomously learn to improve its performance by specializing its skill parameter selection policy to the particular objects, goals, and constraints in its environment. In this work, we focus on the active learning problem of choosing which skills to practice to maximize expected future task success. We propose that the robot should estimate the competence of each skill, extrapolate the competence (asking: “how much would the competence improve through practice?”), and situate the skill in the task distribution through competence- aware planning. This approach is implemented within a fully autonomous system where the robot repeatedly plans, practices, and learns without any environment resets. Through experiments in simulation, we find that our approach learns effective pa- rameter policies more sample-efficiently than several baselines. Experiments in the real-world demonstrate our approach’s ability to handle noise from perception and control and improve the robot’s ability to solve two long-horizon mobile-manipulation tasks after a few hours of autonomous practice. Project website: http://ees.csail.mit.edumore » « less
-
Learning a robot motor skill from scratch is impractically slow; so much so that in practice, learning must typically be bootstrapped using human demonstration. However, relying on human demonstration necessarily degrades the autonomy of robots that must learn a wide variety of skills over their operational lifetimes. We propose using kinematic motion planning as a completely autonomous, sample efficient way to bootstrap motor skill learning for object manipulation. We demonstrate the use of motion planners to bootstrap motor skills in two complex object manipulation scenarios with different policy representations: opening a drawer with a dynamic movement primitive representation, and closing a microwave door with a deep neural network policy. We also show how our method can bootstrap a motor skill for the challenging dynamic task of learning to hit a ball off a tee, where a kinematic plan based on treating the scene as static is insufficient to solve the task, but sufficient to bootstrap a more dynamic policy. In all three cases, our method is competitive with human-demonstrated initialization, and significantly outperforms starting with a random policy. This approach enables robots to to efficiently and autonomously learn motor policies for dynamic tasks without human demonstration.more » « less
-
We measure the labor-demand effects of two simultaneous forms of technological change—automation of production processes and consolidation of parts. We collect detailed shop-floor data from four semiconductor firms with different levels of automation and consolidation. Using the O*NET survey instrument, we collect novel task data for operator laborers that contains process-step level skill requirements, including operations and control, near vision, and dexterity requirements. We then use an engineering process model to separate the effects of the distinct technological changes on these process tasks and operator skill requirements. Within an occupation, we show that aggregate measures of technological change can mask the opposing skill biases of multiple simultaneous technological changes. In our empirical context, automation polarizes skill demand as routine, codifiable tasks requiring low and medium skills are executed by machines instead of humans, whereas the remaining and newly created human tasks tend to require low and high skills. Consolidation converges skill demand as formerly divisible low and high skill tasks are transformed into a single indivisible task with medium skill requirements and higher cost of failure. We conclude by developing a new theory for how the separability of tasks mediates the effect of technology change on skill demand by changing the divisibility of labor.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
