Active Reward Learning for Co-Robotic Vision Based Exploration in Bandwidth Limited Environments
© 2020 IEEE. We present a novel POMDP problem formulation for a robot that must autonomously decide where to go to collect new and scientifically relevant images given a limited ability to communicate with its human operator. From this formulation we derive constraints and design principles for the...
Main Authors: | Jamieson, Stewart Christopher (Author), How, Jonathan P (Author), Girdhar, Yogesh (Author) |
---|---|
Other Authors: | Joint Program in Applied Ocean Physics and Engineering (Contributor), Woods Hole Oceanographic Institution (Contributor) |
Format: | Article |
Language: | English |
Published: |
IEEE,
2021-12-14T18:22:01Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Active Reward Learning for Co-Robotic Vision Based Exploration in Bandwidth Limited Environments
Published: (2021) -
Enabling human-robot cooperation in scientific exploration of bandwidth-limited environments
by: Jamieson, Stewart Christopher.
Published: (2020) -
BANDWIDTH LIMITED 320 MBPS TRANSMITTER
by: Anderson, Christopher
Published: (1996) -
Scalable reward learning from demonstration
by: Michini, Bernard J., et al.
Published: (2015) -
The Limitations of Reward Effects on Saccade Latencies: An Exploration of Task-Specificity and Strength
by: Stephen Dunne, et al.
Published: (2019-05-01)