When the Past Shapes Action: Understanding Embodied Memory
Overview
This paper surveys embodied memory as a mechanism for agents to retain, retrieve, and update information from past observations beyond immediate perception. It organizes existing approaches into six fundamental requirements (world-state persistence, task progress, belief maintenance, experiential learning) and eight architectural categories (recurrent states, fast weights, visual/symbolic representations, spatial memory, experience-based systems). The authors analyze capabilities, limitations, and benchmark evaluations to distinguish genuine memory use from general performance, identifying open challenges in experience selection, belief consistency, and knowledge consolidation for lifelong embodied intelligence.
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalWhen the Past Shapes Action: Understanding Embodied Memory
This paper surveys embodied memory as a mechanism for agents to retain, retrieve, and update information from past observations beyond immediate perception. It organizes existing approaches into six fundamental requirements (world-state persistence, task progress, belief maintenance, experiential learning) and eight architectural categories (recurrent states, fast weights, visual/symbolic representations, spatial memory, experience-based systems). The authors analyze capabilities, limitations, and benchmark evaluations to distinguish genuine memory use from general performance, identifying open challenges in experience selection, belief consistency, and knowledge consolidation for lifelong embodied intelligence.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).