Visual Forecasting as a Mid-level Representation for Avoidance

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.

Authors

• Hsuan-Kung Yang
• Tsung-Chih Chiang
• Ting-Ru Liu
• Chun-Wei Huang
• Jou-Min Liu
• Chun-Yi Lee

Keywords

• Visualization
• Navigation
• Autonomous agents
• Trajectory
• Forecasting
• Collision avoidance
• Intelligent robots
• Engines
• Mid-level Representation
• Simulation Environment
• Bounding Box
• Real-world Scenarios
• Future Trajectories
• Obstacle Avoidance
• Visual Strategies
• Dynamic Objects
• Navigation In Environments
• Object Trajectory
• Deep Neural Network
• Object Detection
• Pedestrian
• Real-world Setting
• Types Of Representations
• Semantic Segmentation
• Maximum Entropy
• Model Predictive Control
• Forecast Accuracy
• Deep Reinforcement Learning Agent
• Constant Velocity Model
• Deep Reinforcement Learning
• Unmanned Ground Vehicles
• Future Position
• Overview Of Framework
• Markov Decision Process
• Performance Of Agents
• Historical Trajectory
• High-dimensional State Space