🗺️ 领域演进总图

按影响力查看文本列表

1. AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
2. Extreme Parkour with Legged Robots
3. BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
4. ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
5. ThriftyDAgger: Budget-aware novelty and risk gating for interactive imitation learning
6. HG-DAgger: Interactive Imitation Learning with Human Experts
7. Constrained Policy Optimization
8. Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark
9. Human Motion Diffusion Model (MDM)
10. Learning Whole-Body Humanoid Locomotion via Motion Generation and Motion Tracking
11. MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding
12. CALM: Conditional Adversarial Latent Models for Directable Virtual Characters
13. RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
14. OpenVLA: An Open-Source Vision-Language-Action Model
15. SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
16. MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives
17. DReCon: Data-Driven Responsive Control of Physics-Based Characters
18. A Scalable Perceptive Parkour Framework for Humanoids
19. OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning
20. LifeLong-RFT: Continual Learning VLA Models via Reinforcement Fine-Tuning
21. Alias-Free Generative Adversarial Networks (StyleGAN3)
22. Learning Dexterous In-Hand Manipulation
23. Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-Expert Distillation and RL Fine-Tuning
24. UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data
25. Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware (ACT / ALOHA)
26. Open X-Embodiment: Robotic Learning Datasets and RT-X Models
27. UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
28. Learning robust perceptive locomotion for quadrupedal robots in the wild (ANYmal-C in the wild)
29. Scalable Muscle-Actuated Human Simulation and Control
30. GR00T N1.x (NVIDIA humanoid VLA foundation model, 2026 iteration)
31. gradSim: Differentiable Simulation for System Identification
32. DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes
33. GPC: Large-Scale Generative Pretraining for Transferable Motor Control
34. EgoMimic: Scaling Imitation Learning via Egocentric Video
35. ControlVAE: Model-based Learning of Generative Controllers for Physics-based Characters
36. InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions
37. DexImit: Learning Bimanual Dexterous Manipulation from Monocular Human Videos
38. TACTO: A Fast, Flexible, and Open-source Simulator for High-Resolution Vision-based Tactile Sensors
39. OpenVLA-OFT: Fine-Tuning Vision-Language-Action Models with Effective and Efficient Multi-Token Action Tokens
40. Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes
41. WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control
42. ILSA: Incremental Learning for Robot Shared Autonomy
43. Mobile ALOHA: Learning Bimanual Mobile Manipulation using Low-Cost Whole-Body Teleoperation
44. RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
45. Real-Time Whole-Body Teleoperation of a Humanoid Robot Using IMU-Based Motion Capture with Sim2Sim and Sim2Real Validation