How can we enable users to create effective, perception-driven task plans for collaborative robots? We conducted a 35-person user study with the Behavior Tree-based CoSTAR system to determine which strategies for end user creation of generalizable robot task plans are most usable and effective. CoSTAR allows domain experts to author complex, perceptually grounded task plans for collaborative robots. As a part of CoSTAR's wide range of capabilities, it allows users to specify SmartMoves: abstract goals such as "pick up component A from the right side of the table." Users were asked to perform pick-and-place assembly tasks with either SmartMoves or one of three simpler baseline versions of CoSTAR. Overall, participants found CoSTAR to be highly usable, with an average System Usability Scale score of 73.4 out of 100. SmartMove also helped users perform tasks faster and m ore effectively; all SmartMove users completed the first two tasks, while not all users completed the tasks using other strategies. SmartMove users showed better performance vs. baseline methods for incorporating perception across all three tasks.
more »
« less
CoSTAR: Instructing collaborative robots with behavior trees and vision
For collaborative robots to become useful, end users who are not robotics experts must be able to instruct
them to perform a variety of tasks.
With this goal in mind, we developed a system for end‐user creation of robust task plans with a broad range of
capabilities. CoSTAR: the Collaborative System for Task Automation and Recognition} is our winning entry in
the 2016 KUKA Innovation Award competition at the Hannover Messe trade show, which this year focused on
Flexible Manufacturing. CoSTAR is unique in how it creates natural abstractions that use perception to
represent the world in a way users can both understand and utilize to author capable and robust task plans.
Our Behavior Tree‐based task editor integrates high‐level information from known object segmentation and
pose estimation with spatial reasoning and robot actions to create robust task plans. We describe the crossplatform
design and implementation of this system on multiple industrial robots and evaluate its suitability for
a wide variety of use cases.
more »
« less
- Award ID(s):
- 1637949
- NSF-PAR ID:
- 10047467
- Date Published:
- Journal Name:
- ICRA 2017
- Page Range / eLocation ID:
- 564 to 571
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
How can we enable users to create effective, perception-driven task plans for collaborative robots? We conducted a 35-person user study with the Behavior Tree-based CoSTAR system to determine which strategies for end user creation of generalizable robot task plans are most usable and effective. CoSTAR allows domain experts to author complex, perceptually grounded task plans for collaborative robots. As a part of CoSTAR's wide range of capabilities, it allows users to specify SmartMoves: abstract goals such as "pick up component A from the right side of the table." Users were asked to perform pick-and-place assembly tasks with either SmartMoves or one of three simpler baseline versions of CoSTAR. Overall, participants found CoSTAR to be highly usable, with an average System Usability Scale score of 73.4 out of 100. SmartMove also helped users perform tasks faster and more effectively; all SmartMove users completed the first two tasks, while not all users completed the tasks using the other strategies. SmartMove users showed better performance for incorporating perception across all three tasks.more » « less
-
We present V.Ra, a visual and spatial programming system for robot-IoT task authoring. In V.Ra, programmable mobile robots serve as binding agents to link the stationary IoTs and perform collaborative tasks. We establish an ecosystem that coherently connects the three key elements of robot task planning , the human, robot and IoT, with one single mobile AR device. Users can perform task authoring with the Augmented Reality (AR) handheld interface, then placing the AR device onto the mobile robot directly transfers the task plan in a what-you-do-is-what-robot-does (WYDWRD) manner. The mobile device mediates the interactions between the user, robot, and the IoT oriented tasks, and guides the path planning execution with the embedded simultaneous localization and mapping (SLAM) capability. We demonstrate that V.Ra enables instant, robust and intuitive room-scale navigatory and interactive task authoring through various use cases and preliminary studies.more » « less
-
Collaborative robots promise to transform work across many industries and promote “human-robot teaming” as a novel paradigm. However, realizing this promise requires the understanding of how existing tasks, developed for and performed by humans, can be effectively translated into tasks that robots can singularly or human-robot teams can collaboratively perform. In the interest of developing tools that facilitate this process we present Authr, an end-to-end task authoring environment that assists engineers at manufacturing facilities in translating existing manual tasks into plans applicable for human-robot teams and simulates these plans as they would be performed by the human and robot. We evaluated Authr with two user studies, which demonstrate the usability and effectiveness of Authr as an interface and the benefits of assistive task allocation methods for designing complex tasks for human-robot teams. We discuss the implications of these findings for the design of software tools for authoring human-robot collaborative plans.more » « less
-
null (Ed.)With growing access to versatile robotics, it is beneficial for end users to be able to teach robots tasks without needing to code a control policy. One possibility is to teach the robot through successful task executions. However, near-optimal demonstrations of a task can be difficult to provide and even successful demonstrations can fail to capture task aspects key to robust skill replication. Here, we propose a learning from demonstration (LfD) approach that enables learning of robust task definitions without the need for near-optimal demonstrations. We present a novel algorithmic framework for learning task specifications based on the ergodic metric—a measure of information content in motion. Moreover, we make use of negative demonstrations— demonstrations of what not to do—and show that they can help compensate for imperfect demonstrations, reduce the number of demonstrations needed, and highlight crucial task elements improving robot performance. In a proof-of-concept example of cart-pole inversion, we show that negative demonstrations alone can be sufficient to successfully learn and recreate a skill. Through a human subject study with 24 participants, we show that consistently more information about a task can be captured from combined positive and negative (posneg) demonstrations than from the same amount of just positive demonstrations. Finally, we demonstrate our learning approach on simulated tasks of target reaching and table cleaning with a 7-DoF Franka arm. Our results point towards a future with robust, data efficient LfD for novice users.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICRA.2017.7989070
