Interactive Tuning of Robot Program Parameters via Expected Divergence Maximization

Mattia Racca, Ville Kyrki, Maya Cakmak

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

7 Sitaatiot (Scopus)
224 Lataukset (Pure)


Enabling diverse users to program robots for different applications is critical for robots to be widely adopted. Most of the new collaborative robot manipulators come with intuitive programming interfaces that allow novice users to compose robot programs and tune their parameters. However, parameters like motion speeds or exerted forces cannot be easily demonstrated and often require manual tuning, resulting in a tedious trial-and-error process. To address this problem, we formulate tuning of one-dimensional parameters as an Active Learning problem where the learner iteratively refines its estimate of the feasible range of parameter values, by selecting informative queries. By executing the parametrized actions, the learner gathers the user's feedback, in the form of directional answers ("higher,'' "lower,'' or "fine''), and integrates it in the estimate. We propose an Active Learning approach based on Expected Divergence Maximization for this setting and compare it against two baselines with synthetic data. We further compare the approaches on a real-robot dataset obtained from programs written with a simple Domain-Specific Language for a robot arm and manually tuned by expert users (N=8) to perform four manipulation tasks. We evaluate the effectiveness and usability of our interactive tuning approach against manual tuning with a user study where novice users (N=8) tuned parameters of a human-robot hand-over program.
OtsikkoProceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction, HRI'20
ISBN (elektroninen)978-1-4503-6746-2
DOI - pysyväislinkit
TilaJulkaistu - 2020
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaACM/IEEE International Conference on Human-Robot Interaction - Cambridge, Iso-Britannia
Kesto: 23 maalisk. 202026 maalisk. 2020
Konferenssinumero: 15


NimiACM/IEEE International Conference on Human-Robot Interaction
ISSN (painettu)2167-2121
ISSN (elektroninen)2167-2148


ConferenceACM/IEEE International Conference on Human-Robot Interaction


Sukella tutkimusaiheisiin 'Interactive Tuning of Robot Program Parameters via Expected Divergence Maximization'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä