Real-World Robot Control Based on Contrastive Deep Active Inference With Demonstrations
Despite significant advances in robotics and deep learning, the ability of robots to perceive and act remain far below that of humans. To bridge this gap, we utilize active inference, a framework based on the free-energy principle that accounts for various human brain functions. Despite the utility...
Saved in:
| Main Authors: | Kentaro Fujii, Takuya Isomura, Shingo Murata |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10710342/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Comparing Skill Transfer Between Full Demonstrations and Segmented Sub-Tasks for Neural Dynamic Motion Primitives
by: Geoffrey Hanks, et al.
Published: (2024-12-01) -
Modeling Active Learning in a Robot Collective
by: Mehmet Dinçer Erbaş
Published: (2020-06-01) -
Segment, Compare, and Learn: Creating Movement Libraries of Complex Task for Learning from Demonstration
by: Adrian Prados, et al.
Published: (2025-01-01) -
Robot Task-Constrained Optimization and Adaptation with Probabilistic Movement Primitives
by: Guanwen Ding, et al.
Published: (2024-12-01) -
Utilizing Demonstrations in Teaching, with an Example Demonstration of Propagation via Cuttings
by: Isabella Damiani, et al.
Published: (2018-05-01)