Memory Centric Power Allocation for Multi-Agent Embodied Question Answering

TL;DR

This paper introduces a memory-focused power allocation method for multi-agent embodied question answering, emphasizing memory quality over sensing or computation, and demonstrates significant performance improvements.

Contribution

It proposes a novel QoM model based on GAE and a power allocation strategy that prioritizes high-QoM robots under resource constraints.

Findings

MCPA improves performance metrics across various scenarios.

Transmit powers are proportional to GAE error probability.

The QoM model effectively assesses memory retrieval quality.

Abstract

This paper considers multi-agent embodied question answering (MA-EQA), which aims to query robot teams on what they have seen over a long horizon. In contrast to existing edge resource management methods that emphasize sensing, communication, or computation performance metrics, MA-EQA emphasizes the memory qualities. To cope with this paradigm shift, we propose a quality of memory (QoM) model based on generative adversarial exam (GAE), which leverages forward simulation to assess memory retrieval and uses the resulting exam scores to compute QoM values. Then we propose memory centric power allocation (MCPA), which maximizes the QoM function under communication resource constraints. Through asymptotic analysis, it is found that the transmit powers are proportional to the GAE error probability, thus prioritizing towards high-QoM robots. Extensive experiments demonstrate that MCPA achieves significant improvements over extensive benchmarks in terms of diverse metrics in various scenarios.