Visual Forecasting as a Mid-level Representation for Avoidance

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Hsuan-Kung, Chiang, Tsung-Chih, Liu, Ting-Ru, Huang, Chun-Wei, Liu, Jou-Min, Lee, Chun-Yi
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913564303818752
author Yang, Hsuan-Kung
Chiang, Tsung-Chih
Liu, Ting-Ru
Huang, Chun-Wei
Liu, Jou-Min
Lee, Chun-Yi
author_facet Yang, Hsuan-Kung
Chiang, Tsung-Chih
Liu, Ting-Ru
Huang, Chun-Wei
Liu, Jou-Min
Lee, Chun-Yi
contents The challenge of navigation in environments with dynamic objects continues to be a central issue in the study of autonomous agents. While predictive methods hold promise, their reliance on precise state information makes them less practical for real-world implementation. This study presents visual forecasting as an innovative alternative. By introducing intuitive visual cues, this approach projects the future trajectories of dynamic objects to improve agent perception and enable anticipatory actions. Our research explores two distinct strategies for conveying predictive information through visual forecasting: (1) sequences of bounding boxes, and (2) augmented paths. To validate the proposed visual forecasting strategies, we initiate evaluations in simulated environments using the Unity engine and then extend these evaluations to real-world scenarios to assess both practicality and effectiveness. The results confirm the viability of visual forecasting as a promising solution for navigation and obstacle avoidance in dynamic environments.
format Preprint
id arxiv_https___arxiv_org_abs_2310_07724
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Visual Forecasting as a Mid-level Representation for Avoidance
Yang, Hsuan-Kung
Chiang, Tsung-Chih
Liu, Ting-Ru
Huang, Chun-Wei
Liu, Jou-Min
Lee, Chun-Yi
Robotics
Artificial Intelligence
Machine Learning
The challenge of navigation in environments with dynamic objects continues to be a central issue in the study of autonomous agents. While predictive methods hold promise, their reliance on precise state information makes them less practical for real-world implementation. This study presents visual forecasting as an innovative alternative. By introducing intuitive visual cues, this approach projects the future trajectories of dynamic objects to improve agent perception and enable anticipatory actions. Our research explores two distinct strategies for conveying predictive information through visual forecasting: (1) sequences of bounding boxes, and (2) augmented paths. To validate the proposed visual forecasting strategies, we initiate evaluations in simulated environments using the Unity engine and then extend these evaluations to real-world scenarios to assess both practicality and effectiveness. The results confirm the viability of visual forecasting as a promising solution for navigation and obstacle avoidance in dynamic environments.
title Visual Forecasting as a Mid-level Representation for Avoidance
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2310.07724