A user study on human-robot-interactive recovery for industrial assembly problems

Muxfeldt, Arne; Gopinathan, Sugeeth; Coenders, Thilo; Steil, Jochen J.

doi:10.1109/roman.2017.8172398

Cited by 4 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Bajcsy et al [20], demonstrations are required in the form of corrections as input for incremental LfD. Some of the prioritized features are sporadic demonstrations (3), plausibility (10), feasibility (11), recognizability (2), capturing corrections (12) and feedback (9). It is also possible that certain features are intentionally de-prioritized, for instance failed demonstrations are encouraged in Grollman and Billard [27] for improving LfD algorithms.…”

Section: Characterizing Input Methodsmentioning

confidence: 99%

“…2) Free-Hand Manipulation (FHM): In FHM, users perform demonstrations with their hand. Unlike in KG, obtaining precise kinematic measurements and force information of these demonstrations is difficult (12). Instrumented gloves are also expensive and uncommon.…”

Section: Characterizing Input Methodsmentioning

confidence: 99%

“…Prior work has explored techniques for visual [41] and haptic feedback [42]. Similar to KG, TO is naturally instrumented to record kinematic information (12) and provides plausible (10) and feasible (11) movements (assuming that the actual robot is used). Prior work has explored natural interfaces for teleoperation control and compared it to other standard interfaces [4].…”

Section: Characterizing Input Methodsmentioning

confidence: 99%

“…We can use optimization to create feasible trajectories from end-effector paths. 4) Precise Measurement: Many robot control algorithms require precise measurement of position and orientation as well as applied forces and torques during the demonstration (12).…”

Section: Design Of Instrumented Tongsmentioning

confidence: 99%

“…Prior research in HRI has considered either multiple implementations of a single input method such as kinesthetic guidance or teleoperation (e.g., [3]- [8]) or compared multiple input methods including GUI, space mouse, and haptic interface (e.g., [1], [2], [9]- [12]). At a high level, these studies indicate that input methods affect the experience and quality of the demonstrations provided by users.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Characterizing Input Methods for Human-to-Robot Demonstrations

Praveena

Subramani

Mutlu

et al. 2019

2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

Human demonstrations are important in a range of robotics applications, and are created with a variety of input methods. However, the design space for these input methods has not been extensively studied. In this paper, focusing on demonstrations of hand-scale object manipulation tasks to robot arms with two-finger grippers, we identify distinct usage paradigms in robotics that utilize human-to-robot demonstrations, extract abstract features that form a design space for input methods, and characterize existing input methods as well as a novel input method that we introduce, the instrumented tongs. We detail the design specifications for our method and present a user study that compares it against three common input methods: free-hand manipulation, kinesthetic guidance, and teleoperation. Study results show that instrumented tongs provide high quality demonstrations and a positive experience for the demonstrator while offering good correspondence to the target robot.

show abstract