Model Adaption Object Detection System for Robot

TL;DR

This paper introduces a flexible robot object detection system that employs multiple neural networks guided by a meta network, utilizing transfer learning and depthwise convolutions to adapt to changing views and small datasets.

Contribution

It proposes a novel adaptive detection system combining multiple neural networks with a meta network for improved robot guidance in dynamic environments.

Findings

Effective in small dataset scenarios

Adapts to changing robot viewpoints

Utilizes transfer learning for easier training

Abstract

Object detection for robot guidance is a crucial mission for autonomous robots, which has provoked extensive attention for researchers. However, the changing view of robot movement and limited available data hinder the research in this area. To address these matters, we proposed a new vision system for robots, the model adaptation object detection system. Instead of using a single one to solve problems, We made use of different object detection neural networks to guide the robot in accordance with various situations, with the help of a meta neural network to allocate the object detection neural networks. Furthermore, taking advantage of transfer learning technology and depthwise separable convolutions, our model is easy to train and can address small dataset problems.