Shape Your Body: Value Gradients for Multi-Embodiment Robot Design
cs.RO, cs.AI
Submitted: 2026-05-30
Updated: 2026-10-13
Terminology
Sources
- Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design
- Neural Graph Evolution: Towards Efficient Automatic Robot Design
- Task-Agnostic Morphology Evolution
- N-LIMB: Neural Limb Optimization for Efficient Morphological Design
- RoboMorph: Evolving Robot Morphology using Large Language Models
- Multi-embodiment Legged Robot Control as a Sequence Modeling Problem
- Latent Diffeomorphic Co-Design of End-Effectors for Deformable and Fragile Object Manipulation
- Identifying and Exploiting Structure in Robot Co-Design
- Proximal Policy Optimization Algorithms
- Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization
- Policy Evaluation Networks
- Massively Scaling Explicit Policy-conditioned Value Functions
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
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies