COSM2IC: Optimizing Real-Time Multi-Modal Instruction Comprehension

Authors:
Publisher website
Google Scholar
Abstract
Supporting real-time, on-device execution of multi-modal referring instruction comprehension models is an important challenge to be tackled in embodied Human-Robot Interaction. However, state-of-the-art deep learning models are resource-intensive and unsuitable for real-time execution on embedded devices. While model compression can achieve a reduction in computational resources up to a certain point, further optimizations result in a severe drop in accuracy. To minimize this loss in accuracy, we propose the COSM2IC framework, with a lightweight Task Complexity Predictor, that uses multiple sensor inputs to assess the instructional complexity and thereby dynamically switch between a set of models of varying computational intensity such that computationally less demanding models are invoked whenever possible. To demonstrate the benefits of COSM2IC , we utilize a representative human-robot collaborative “table-top target acquisition” task, to curate a new multi-modal instruction dataset where a human issues instructions in a natural manner using a combination of visual, verbal, and gestural (pointing) cues. We show that COSM2IC achieves a 3-fold reduction in comprehension latency when compared to a baseline DNN model while suffering an accuracy loss of only $\sim$ 5%. When compared to state-of-the-art model compression methods, COSM2IC is able to achieve a further 30% reduction in latency and energy consumption for a comparable performance.
Funding Information
  • National Research Foundation
  • NRF Investigatorship (NRF-NRFI05-2019-0007)
  • Ministry of Education - Singapore
  • Academic Research Fund Tier-1 (19-C220-SMU-008)
  • Agency for Science, Technology and Research (A*STAR), Singapore
  • AME Programmatic Funding Scheme (A18A2b0046)

This publication has 21 references indexed in Scilit: