Dynamic Selection of Perception Models for Robotic Control

07/13/2022
by   Bineet Ghosh, et al.
0

Robotic perception models, such as Deep Neural Networks (DNNs), are becoming more computationally intensive and there are several models being trained with accuracy and latency trade-offs. However, modern latency accuracy trade-offs largely report mean accuracy for single-step vision tasks, but there is little work showing which model to invoke for multi-step control tasks in robotics. The key challenge in a multi-step decision making is to make use of the right models at right times to accomplish the given task. That is, the accomplishment of the task with a minimum control cost and minimum perception time is a desideratum; this is known as the model selection problem. In this work, we precisely address this problem of invoking the correct sequence of perception models for multi-step control. In other words, we provide a provably optimal solution to the model selection problem by casting it as a multi-objective optimization problem balancing the control cost and perception time. The key insight obtained from our solution is how the variance of the perception models matters (not just the mean accuracy) for multi-step decision making, and to show how to use diverse perception models as a primitive for energy-efficient robotics. Further, we demonstrate our approach on a photo-realistic drone landing simulation using visual navigation in AirSim. Using our proposed policy, we achieved 38.04 than other competing benchmarks.

READ FULL TEXT

page 1

page 7

page 13

research
08/03/2021

Interpretable Trade-offs Between Robot Task Accuracy and Compute Efficiency

A robot can invoke heterogeneous computation resources such as CPUs, clo...
research
10/24/2022

Perception of the Environment

This chapter discusses the intricacies of cybersecurity agents' percepti...
research
06/22/2021

Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization

When tuning the architecture and hyperparameters of large machine learni...
research
04/13/2022

Task-Driven Data Augmentation for Vision-Based Robotic Control

Today's robots often interface data-driven perception and planning model...
research
08/24/2023

IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency

Efficiently optimizing multi-model inference pipelines for fast, accurat...
research
02/15/2019

Network Offloading Policies for Cloud Robotics: a Learning-based Approach

Today's robotic systems are increasingly turning to computationally expe...
research
04/22/2019

Revisiting Multi-Step Nonlinearity Compensation with Machine Learning

For the efficient compensation of fiber nonlinearity, one of the guiding...

Please sign up or login with your details

Forgot password? Click here to reset