Abstract: This research proposes a novel semi-supervised learning framework FourStr (Four-Stream formed by two two-stream models) that focuses on the improvement of fusion and labeling efficiency for 3D multi-sensor detector. FourStr adopts a multi-sensor single-stage detector named adaptive fusion network (AFNet) as the backbone and trains it through the semi-supervision learning (SSL) strategy Stereo Fusion.
Abstract: Human-made concrete structures require cutting-edge inspection tools to ensure the quality of the construction to meet the applicable building codes and to maintain the sustainability of the aging infrastructure. This paper introduces a wall-climbing robot for metric concrete inspection that can reach difficult-to-access locations with a close-up view for visual data collection and real-time flaws detection and localization.
Abstract: The feature pyramid, which is a vital component of the convolutional neural networks, plays a significant role in several perception tasks, including object detection for autonomous driving. However, how to better fuse multi-level and multi-sensor feature pyramids is still a significant challenge, especially for object detection.
Abstract: Current learning-based 3-D object detection accuracy is heavily impacted by the annotation quality. It is still a challenge to expect an overall high detection accuracy for all classes under different scenarios given the dataset sparsity.
Abstract: Recently significant progress has been made in 3D detection. However, it is still challenging to detect small contour objects under complex scenes. This paper proposes a novel Attention-based Multi-phase Multi-task Fusion (AMMF) that uses point-level, RoI-level, and multi-task fusions to complement the disadvantages of LiDAR and camera, to solve this challenge.
Abstract: Traditional manual wheelchairs have a fixed seat with no movement or angle adjustment, which can seriously affect the user’s comfort and greatly limit user experience. However, the electric wheelchair relies on strong intelligence and automatic features; it can not only realize the multidegree freedom adjustment of the human body and the seat but also has a rich and powerful man–machine control interface, which greatly facilitates and improves the user experience.
Abstract: This paper proposes a real-time multi-scale semantic segmentation network (MsNet). MsNet is a combination of our novel multi-scale fusion with matching attention model (MFMA) as the decoding network and the network searched by asymptotic neural architecture search (ANAS) or MobileNetV3 as the encoding network.
Abstract: Autonomous wheelchairs can address a very large need in many populations by serving as the gateway to a much higher degree of independence and mobility capability. This is due to the fact that the big picture idea for autonomous wheelchairs integration into the transportation chain is to allow for individuals to be able to utilize the Intelligent wheelchair to reach the vehicle (regardless of terrain), mount into autonomous wheelchair that navigates to desired destination, and finally autonomous wheelchair dismounts.
Abstract: The fundamental aspect of unmanned ground vehicle (UGV) navigation, especially over off-road environments, are representations of terrain describing geometry, types, and traversability. One of the typical representations of the environment is digital surface models (DSMs) which efficiently encode geometric information.
Abstract: With the particular passage capability, all-terrain vehicle (ATV) has been widely used for off-road scenarios. In this research, we conduct a lateral sway stability analysis for the suspension mechanism of a general vehicle and establish a mathematical model of static and dynamic stability based on the maximum lateral sway angle and lateral sway acceleration, by considering the combined angular stiffness of independent suspension, angular stiffness of the lateral stabilizer bar and vertical stiffness of tires.