SAKI: Skill Assembly and Kinematic Imitation from Human Videos for Long-Horizon Mobile Manipulation

arXiv:2609.36031 · cs.RO · Submitted 2026-09-28 · Read on arXiv

cs.RO

Submitted: 2026-09-28

Updated: 2026-09-28

Project page: https://aus.bot/research/saki/Abstract

Terminology

• Alignment — 8× in this paper · explained in 1 episode
• Grounding — 5× in this paper · explained in 3 episodes
• Skill Assembly and Kinematic Imitation — 4× in this paper
• Adaptation — 3× in this paper · explained in 1 episode
• Ablation — 2× in this paper · explained in 1 episode
• Trace — 2× in this paper · explained in 2 episodes
• Affordance — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• IEEE International Conference on Robotics and Automation — 1× in this paper
• Information Gain — 1× in this paper · explained in 2 episodes
• Point Clouds — 1× in this paper · explained in 2 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes

Sources

• Vision-based Manipulation from Single Human Video with Open-World Object Graphs
• DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation
• BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation
• SPOT: SE(3) Pose Trajectory Diffusion for Object-Centric Manipulation
• ScrewMimic: Bimanual Imitation from Human Videos with Screw Space Projection
• Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation
• SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields
• VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
• ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation
• Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation
• HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations
• HRT1: One-Shot Human-to-Robot Trajectory Transfer for Mobile Manipulation
• Inner Monologue: Embodied Reasoning through Planning with Language Models
• MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
• DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning
• Tri-Manual Visuomotor Imitation Learning of Robot Policies
• Worlds in One Demo: A Synthetic Data Engine for Learning Open-World Mobile Manipulation
• Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow
• RoboReact: Agentic Skill Distillation from Generated Egocentric Videos for Generalizable Whole-Body Manipulation
• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving