HiPAN enables quadruped robots to navigate unstructured 3D environments more successfully by combining a high-level posture-adaptive policy with a low-level controller and curriculum learning on depth images.
Moe-loco: Mixture of experts for multitask locomotion
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
CoRDE uses concept-prior variational distillation and LoRA-based expert pools to route diffusion models for structurally generalizable robot manipulation policies.
SigLoMa enables dynamic loco-manipulation on quadrupeds from ego-centric 5 Hz vision alone by using Sigma Points for scalable exteroception, an ego-centric Kalman Filter for high-rate state estimation, and an active sampling curriculum, matching expert human teleoperation performance.
A single reinforcement learning policy jointly trains multiple locomotion skills for wheeled-legged robots with DC-motor constraints and learns a proprioceptive skill selector for adaptive behavior.
A two-stage distillation plus reinforced fine-tuning approach produces a single humanoid locomotion controller that adapts across skills and irregular terrains.
LiMoDE uses dynamic MoE pre-training on motion cues followed by lifelong expert addition for continuous robot task adaptation.
Sparsely gated MoE policies double the success rate of a real Unitree Go2 quadruped on large-obstacle parkour versus matched-active-parameter MLP baselines while cutting inference time compared with a scaled-up MLP.
citing papers explorer
-
HiPAN: Hierarchical Posture-Adaptive Navigation for Quadruped Robots in Unstructured 3D Environments
HiPAN enables quadruped robots to navigate unstructured 3D environments more successfully by combining a high-level posture-adaptive policy with a low-level controller and curriculum learning on depth images.
-
CoRDE: Concept-Prior Routed Diffusion Experts for Structural Generalization in Robot Manipulation
CoRDE uses concept-prior variational distillation and LoRA-based expert pools to route diffusion models for structurally generalizable robot manipulation policies.
-
SigLoMa: Learning Open-World Quadrupedal Loco-Manipulation from Ego-Centric Vision
SigLoMa enables dynamic loco-manipulation on quadrupeds from ego-centric 5 Hz vision alone by using Sigma Points for scalable exteroception, an ego-centric Kalman Filter for high-rate state estimation, and an active sampling curriculum, matching expert human teleoperation performance.
-
MUJICA: Multi-skill Unified Joint Integration of Control Architecture for Wheeled-Legged Robots
A single reinforcement learning policy jointly trains multiple locomotion skills for wheeled-legged robots with DC-motor constraints and learns a proprioceptive skill selector for adaptive behavior.
-
Towards Adaptive Humanoid Control via Multi-Behavior Distillation and Reinforced Fine-Tuning
A two-stage distillation plus reinforced fine-tuning approach produces a single humanoid locomotion controller that adapts across skills and irregular terrains.
-
LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective
LiMoDE uses dynamic MoE pre-training on motion cues followed by lifelong expert addition for continuous robot task adaptation.
-
Quadruped Parkour Learning: Sparsely Gated Mixture of Experts with Visual Input
Sparsely gated MoE policies double the success rate of a real Unitree Go2 quadruped on large-obstacle parkour versus matched-active-parameter MLP baselines while cutting inference time compared with a scaled-up MLP.