This paper discusses three points inspired by Skraaning and Jamieson’s perspective on automation failure: (a) the limitations of the automation failure concept with expanding system boundaries; (b) parallels between the failure to grasp automation failure and the failure to grasp trust in automation; (c) benefits of taking a pluralistic approach to definitions in sociotechnical systems science. While a taxonomy of automation-involved failures may not directly improve our understanding of how to prevent those failures, it could be instrumental for identifying hazards during test and evaluation of operational systems.
more »
« less
Modeling Grasp Type Improves Learning-Based Grasp Planning
- Award ID(s):
- 1657596
- PAR ID:
- 10089725
- Date Published:
- Journal Name:
- IEEE Robotics and Automation Letters
- Volume:
- 4
- Issue:
- 2
- ISSN:
- 2377-3774
- Page Range / eLocation ID:
- 784 to 791
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This work provides a framework for a workspace aware online grasp planner. This framework greatly improves the performance of standard online grasp planning algorithms by incorporating a notion of reachability into the online grasp planning process. Offline, a database of hundreds of thousands of unique end-effector poses were queried for feasibility. At runtime, our grasp planner uses this database to bias the hand towards reachable end-effector configurations. The bias keeps the grasp planner in accessible regions of the planning scene so that the resulting grasps are tailored to the situation at hand. This results in a higher percentage of reachable grasps, a higher percentage of successful grasp executions, and a reduced planning time. We also present experimental results using simulated and real environments.more » « less