Robocasa-Mem: Benchmarking Environment and Process Memory in Long-Horizon Mobile Manipulation
cs.RO
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/SiHhangChen/RoboCasa-Mem
Project page: https://sihhangchen.github.io/RoboCasa-Mem
Terminology
Sources
- Qwen3-VL Technical Report
- RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design
- Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning
- RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
- BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation
- UniMem: Unifying Visual and Textual Memory in VLAs for Non-Markovian Tasks
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- MemER: Scaling Up Memory for Robot Control via Experience Retrieval
- Habitat 2.0: Training Home Assistants to Rearrange their Habitat
- MEM: Multi-Scale Embodied Memory for Vision Language Action Models
- Mimir: A Neuro-Symbolic Memory System with Dynamic Grounding for Embodied Agents in Interactive Environments
- EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies
- KEMO: Event-Driven Keyframe Memory for Long-Horizon Robot Manipulation with VLA Policies
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation