No AI summary available for this article.
Why It Matters
Complex robotic manipulation tasks frequently require a long-term memory of past events and actions.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditioning on full histories renders policies prone to spurious correlations and degrades performance, many approaches to policy memory involve compressing historical information through expensive VLM queries in-the-loop to process only task-salient information. In this paper, we propose an alternative approach in which computationally intensive VLM queries are made during train-time to learn a lightweight latent memory that can be efficiently queried at deployment time. Our representation...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.20820v1 · Indexed about 1 hour ago