SERF: Spatiotemporal Environment and Robot Feature Map for Long-Horizon Mobile Manipulation

arXiv:2606.12956 · cs.RO · Submitted 2026-06-11 · Read on arXiv

cs.RO

Submitted: 2026-06-11

Updated: 2026-10-12

Project page: https://existentialrobotics.org/serf

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Gemini Robotics: Bringing AI into the Physical World
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• $\pi^{*}_{0.6}$: a VLA That Learns From Experience
• MEM: Multi-Scale Embodied Memory for Vision Language Action Models
• EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation
• mindmap: Spatial Memory in Deep Feature Maps for 3D Action Policies
• DINOv3
• Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge
• Representation Learning with Contrastive Predictive Coding

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