A teacher-student RL policy distillation approach combined with procedural tunnel generation enables quadruped robots to traverse narrow tunnels consistently in both simulation and real-world tests.
A reduction of imitation learning and structured prediction to no-regret online learning,
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
-
Robot Squid Game: Quadrupedal Locomotion for Traversing Narrow Tunnels
A teacher-student RL policy distillation approach combined with procedural tunnel generation enables quadruped robots to traverse narrow tunnels consistently in both simulation and real-world tests.