Intelligent Object Exploration

Gaschler, Robert; Katz, Dov; Grund, Martin; Frensch, Peter A.; Brock, Oliver

doi:10.5772/25836

Cited by 5 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While prior results of tasks placing little load on psychomotor control showed substantial shortcut usage based on the discovery of simple regularities (Gaschler et al, 2012 ), this was not the case in the current setup with long chains, two-handed operation and kinematic feedback. The right panel of the graph does not suggest any differences in exploration time for participants with vs. without option for simplification.…”

Section: Resultsmentioning

confidence: 52%

“…For some participants, the 2nd joint from the left was always revolute. Such a redundancy was discovered by the participants in our earlier work with shorter chains and a simplistic interaction mode (Gaschler et al, 2012 ). Here, we wanted to test whether this would extent to situations with longer structures and enriched interaction opportunities.…”

Section: Methodsmentioning

confidence: 87%

“…One means to characterize learning is to test if this learning is bound to particular material trained or generalizes to variants not practiced or practiced less often (cf. Kramer et al, 1991 ; Katz et al, 2008 ; Gaschler et al, 2012 ). For instance, Katz and Brock ( 2008 ) found that a simulated robot could transfer 30% of the gain in speed of exploration from a shorter chain (it was trained on) to a longer chain and Gaschler et al ( 2012 ) found that once a redundancy in the task material is discovered, it is transferred to novel stimuli.…”

Section: The Present Studymentioning

confidence: 99%

“…We tested the exploration behavior on randomly generated chains in a human sample ( N = 19). Similar to Gaschler et al ( 2012 ), the task was to identify the joints of the chain, but this time by physical exploration rather than by keyboard-commanded discrete tests. The structure of the chain was explored by exerting force at blocks or joints of the chain by pulling or pushing (Figure 1A ).…”

Section: The Present Studymentioning

confidence: 99%

“…Exploration problems are often presented to humans as symbolic problem solving tasks. These tasks place minimal demands on physical interaction with the environment so that neither its potential costs nor its potential scaffolding function in the problem solving process can be evaluated (e.g., Wason, 1960 ; Gaschler et al, 2012 ; Wakebe et al, 2012 ). Note that in some cases, symbolic problem solving has been combined with elaborate physical interaction (e.g., Klahr and Dunbar, 1988 ).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Learning to explore the structure of kinematic objects in a virtual environment

et al. 2015

Self Cite

View full text Add to dashboard Cite

The current study tested the quantity and quality of human exploration learning in a virtual environment. Given the everyday experience of humans with physical object exploration, we document substantial practice gains in the time, force, and number of actions needed to classify the structure of virtual chains, marking the joints as revolute, prismatic, or rigid. In line with current work on skill acquisition, participants could generalize the new and efficient psychomotor patterns of object exploration to novel objects. On the one hand, practice gains in exploration performance could be captured by a negative exponential practice function. On the other hand, they could be linked to strategies and strategy change. After quantifying how much was learned in object exploration and identifying the time course of practice-related gains in exploration efficiency (speed), we identified what was learned. First, we identified strategy components that were associated with efficient (fast) exploration performance: sequential processing, simultaneous use of both hands, low use of pulling rather than pushing, and low use of force. Only the latter was beneficial irrespective of the characteristics of the other strategy components. Second, we therefore characterized efficient exploration behavior by strategies that simultaneously take into account the abovementioned strategy components. We observed that participants maintained a high level of flexibility, sampling from a pool of exploration strategies trading the level of psycho-motoric challenges with exploration speed. We discuss the findings pursuing the aim of advancing intelligent object exploration by combining analytic (object exploration in humans) and synthetic work (object exploration in robots) in the same virtual environment.

show abstract

Section: Resultsmentioning

confidence: 52%

Section: Methodsmentioning

confidence: 87%

Section: The Present Studymentioning

confidence: 99%

Section: The Present Studymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning to explore the structure of kinematic objects in a virtual environment

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

Building object models through interactive perception and foveated vision

Bevec

Ude

2015

Advanced Robotics

View full text Add to dashboard Cite

Autonomous robots that operate in unstructured environments must be able to seamlessly expand their knowledge base. To detect and manipulate previously unknown objects, a robot should be able to acquire new object knowledge even when no prior information about the objects or the environment is available. Additional information that is needed to identify new objects can come through motion cues induced by interactive manipulation. In the proposed system, changes in the scene are caused by a teacher manipulating the object to be learned. We propose to improve visual object learning and recognition by exploiting the advantages of foveated vision. The proposed approach first creates object hypotheses in peripheral stereo cameras. By directing its attention towards the identified object area in the foveal views, the robot can conduct a more thorough investigation of a smaller area of the scene, which is seen in higher resolution. We compare two methods for validating the hypotheses in the foveal views and experimentally show the advantages of foveated vision compared to stereo vision with a fixed field of view.

show abstract

Pushing and grasping for autonomous learning of object models with foveated vision

Bevec

Ude

2015

2015 International Conference on Advanced Robotics (ICAR)

View full text Add to dashboard Cite

Intelligent Object Exploration

Cited by 5 publications

References 27 publications

Learning to explore the structure of kinematic objects in a virtual environment

Learning to explore the structure of kinematic objects in a virtual environment

Building object models through interactive perception and foveated vision

Pushing and grasping for autonomous learning of object models with foveated vision

Contact Info

Product

Resources

About