Towards automatic transfer of human skills for robotic assembly

Newman, Wyatt S.; Birkhimer, Craig; Hebbar, Ramachandra

doi:10.1109/iros.2003.1249250

Cited by 10 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robots intended to work with humans often incorporate force-sensing technologies and control algorithms to enable human-guided training [6], object handling [7,8], and safe collision handling [9].…”

Section: Robotics In Assemblymentioning

confidence: 99%

Best Practices and Performance Metrics Using Force Control for Robotic Assembly

Marvel¹,

Falco²

2012

View full text Add to dashboard Cite

Section: Robotics In Assemblymentioning

confidence: 99%

Best Practices and Performance Metrics Using Force Control for Robotic Assembly

Marvel¹,

Falco²

2012

View full text Add to dashboard Cite

“…Moreover, from an assembly line point of view, to accommodate critical cycle-time requirements [4], we need to comply with a preset maximum localization time. Hence, after a pre-determined number of iterations we switch from the localization strategy to a compliant form of assembly [5] that can handle the reduced uncertainty-as will be described below-or a blind search [6]- [8].…”

Section: Localization Strategy Using Particle Filtersmentioning

confidence: 99%

“…In every assembly trial the localization phase was followed by a previously-devised compliant assembly phase [5]. The localization phase provides an estimate of the hole configuration and the compliant phase attempts to assemble the peg into the estimated hole configuration.…”

Section: B Robotic Assembliesmentioning

confidence: 99%

Particle filtering for localization in robotic assemblies with position uncertainty

Chhatpar

Branicky

2005

2005 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

This paper deals with the class of robotic assemblies where position uncertainty far exceeds assembly clearance, and visual assistance is not available to resolve the uncertainty. Under this scenario, we can implement a localization strategy that resolves the uncertainty using a pre-acquired map of all possible peg-hole contact configurations. Prior to assembly, the strategy explores the contact configuration space (C-space) by sequentially bringing the peg (under different configurations) into contact with the stationary (fixtured) hole and matching the contact configurations thus recorded with the map. The different peg configurations can be actively chosen to maximize uncertainty-reduction. However, with a sampled map of the contact C-space, discretization errors are introduced, and implementing deterministic matching (at the fine-grained level necessary for assembly) would soon become prohibitively expensive in terms of computation. Additionally, with global initial uncertainty, multiple solutions abound in our localization problem. In this paper, we introduce a particle filter implementation which can not only handle the discretization errors in map-matching, but also track multiple solutions simultaneously. The particle filter implementation was validated on computer simulations of round and square peg-in-hole assemblies, before testing it on corresponding actual robotic assemblies. The implementation was highly successful on both the assemblies, reducing the uncertainty by more than 95% and making it easy for a previously-devised compliant strategy to achieve assembly. Results from the simulations and actual assemblies are reported. We also present a comparison of these results (using random localization: peg moves selected randomly) with preliminary results from assemblies using active localization.

show abstract

“…For simplicity, we assume that the impedance parameters are held constant for the duration of each action-primitive function. We have found that the apparent manipulation skills utilized by humans in performing many useful assemblies can be adequately modeled with a coarse sequence of straightline attractor trajectories [13]. Note that while the attractor trajectory of an action primitive is linear, the corresponding motion of the robot itself may be much more complex, due to dynamic interaction with the environment (e.g., while complying with a kinematic constraint).…”

Section: (Higher Levels)mentioning

confidence: 98%

“…To gain some insights into how to identify and organize such primitives, we have analyzed instrumented human demonstrations of assembly operations [13]. While no two instances of human demonstrations are identical, repetitions are subjectively similar.…”

Section: Primitive Action Functionsmentioning

confidence: 99%

A Client/Server Approach to Open-Architecture, Behavior-Based Robot Programming

Newman

Covitch

May

2nd IEEE International Conference on Space Mission Challenges for Information Technology (SMC-IT'06)

View full text Add to dashboard Cite

This paper describes our progress in the development of a behavior-based, stimulus-response robot control software architecture that is expressly designed to program and execute interactive tasks, including assembly, multi-robot collaborative manipulation, and exploration. The system has been designed to assure stability and safety while maintaining flexibility and achieving expert performance. The architecture incorporates a reactive controller as a behavior server, and applications are written as client programs that can operate either locally or across a network. This organization has been demonstrated to be sufficiently open to support teleoperation tasks as well as human-guided supervisory control and full autonomous functionality.

show abstract

Towards automatic transfer of human skills for robotic assembly

Cited by 10 publications

References 13 publications

Best Practices and Performance Metrics Using Force Control for Robotic Assembly

Best Practices and Performance Metrics Using Force Control for Robotic Assembly

Particle filtering for localization in robotic assemblies with position uncertainty

A Client/Server Approach to Open-Architecture, Behavior-Based Robot Programming

Contact Info

Product

Resources

About