Search papers, labs, and topics across Lattice.
NUSNov 3, 2025This paper introduces a system for autonomous navigation that detects environmental changes using video data from mobile cameras and replans paths accordingly. They propose CUCD, an attention-based change detection model combining UNet and CBAM, and integrate it with a DQN-based reinforcement learning model for path planning. Experiments in simulation and the real world demonstrate the system's ability to effectively detect changes and replan navigation paths.
A drone can now autonomously replan its path in response to detected environmental changes, using a UNet+CBAM change detection model and DQN-based path planning.
Change detection in videos is a crucial task for identifying alterations in an environment, contingent on knowledge of the base environment. In this work, we assume goal-oriented problems and want to develop an autonomous agent that uses video data from mobile cameras to detect environmental changes. The agent then autonomously adjusts its path in response to these detected changes to reach the target. We introduce an attention-based model by combining UNet and Convolution Blocks Attention Module (CBAM) for change detection, named CUCD, and use a Deep Q-Network (DQN) reinforcement learning model to build a system for autonomous path planning. To examine the effectiveness of the system, we design a pipeline connecting a drone, our change detection model, and a path planning model. The experiments conducted in both simulation and the real world show that changes in the environment can be effectively detected and the navigation path appropriately replanned using our method.
