Task-conditioned epistemic uncertainty in foothold predictions enables OOD detection and up to 37% lower feasibility error in uncertainty-aware costmaps for legged robot planning.
Deepgait: Planning and control of quadrupedal gaits using deep reinforcement learning.IEEE Robotics and Automation Letters, 5(2):3699– 3706, 2020
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Task-Conditioned Uncertainty Costmaps for Legged Locomotion
Task-conditioned epistemic uncertainty in foothold predictions enables OOD detection and up to 37% lower feasibility error in uncertainty-aware costmaps for legged robot planning.