An RL-trained quadruped policy, using bidirectional scandots as privileged information and a centerline reward, crosses narrow pipes with obstacles in simulation and on a Unitree Go2.
Robots for pipeline inspection tasks—a survey of design philosophy and implementation technologies,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Quadrupedal Robot Locomotion for Narrow Pipe Inspection
An RL-trained quadruped policy, using bidirectional scandots as privileged information and a centerline reward, crosses narrow pipes with obstacles in simulation and on a Unitree Go2.