Visual Forecasting as a Mid-level Representation for Avoidance

TL;DR

This research explores two distinct strategies for conveying predictive information through visual forecasting: sequences of bounding boxes, and augmented paths, and confirms the viability of visual forecasting as a promising solution for navigation and obstacle avoidance in dynamic environments.

Abstract

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.

Figures (6)

• Figure 1: The demonstrations of (a) the forecasted trajectories and (b) the agents interacting and avoiding pedestrians in the simulated environments.
• Figure 2: An Overview of our framework.
• Figure 3: Visualization of different visual forecasting representation schemes.
• Figure 4: An overview of the simulated environments used in our experiments. The S-Turn environment features an S-shaped path, while Urban Grid Street is a setting with eight intersections.
• Figure 5: Visualization of virtual guidance yang2023vision and visual forecasting.