Dezhen Song from Texas A&M University presented a talk on Co-Modality Active sensing and Perception (C-MAP) for robotics, covering sensor fusion for autonomous vehicles, augmented reality, and remote environmental monitoring. The talk highlighted lessons learned in sensor fusion using autonomous motorcycles and NASA Robonaut as examples. Recent works in robotic remote environment monitoring, especially focused on subsurface surface void and pipeline mapping were discussed. Why it matters: This research explores sensor fusion techniques to enhance robot perception, which could improve the robustness and capabilities of autonomous systems developed and deployed in the Middle East, particularly in challenging environments.
The paper introduces OmniGen, a unified framework for generating aligned multimodal sensor data for autonomous driving using a shared Bird's Eye View (BEV) space. It uses a novel generalizable multimodal reconstruction method (UAE) to jointly decode LiDAR and multi-view camera data through volume rendering. The framework incorporates a Diffusion Transformer (DiT) with a ControlNet branch to enable controllable multimodal sensor generation, demonstrating good performance and multimodal consistency.
KAUST researchers have developed a dual-use wireless sensor system that monitors both traffic congestion and flood incidents in cities. The system combines ultrasonic range finders and infrared thermal sensors to provide real-time, accurate data on traffic flow and roadway flooding. Data is sent to central servers and assimilated with satellite data to form real-time maps and forecasts. Why it matters: This technology can provide up-to-the-minute warnings for flash floods and traffic, enabling rapid emergency response and potentially saving lives in urban environments.
Researchers at MBZUAI have introduced a novel approach to enhance Large Multimodal Models (LMMs) for autonomous driving by integrating 3D tracking information. This method uses a track encoder to embed spatial and temporal data, enriching visual queries and improving the LMM's understanding of driving scenarios. Experiments on DriveLM-nuScenes and DriveLM-CARLA benchmarks demonstrate significant improvements in perception, planning, and prediction tasks compared to baseline models.