Multimodal obstacle detection in unstructured environments with conditional random fields

Reliable obstacle detection and classification in rough and unstructured terrain such as agricultural fields or orchards remains a challenging problem. These environments involve large variations in both geometry and appearance, challenging perception systems that rely on only a single sensor modality. Geometrically, tall grass, fallen leaves, or terrain roughness can mistakenly be perceived as nontraversable or might even obscure actual obstacles. Likewise, traversable grass or dirt roads and obstacles such as trees and bushes might be visually ambiguous. In this paper, we combine appearance‐ and geometry‐based detection methods by probabilistically fusing lidar and camera sensing with semantic segmentation using a conditional random field. We apply a state‐of‐the‐art multimodal fusion algorithm from the scene analysis domain and adjust it for obstacle detection in agriculture with moving ground vehicles. This involves explicitly handling sparse point cloud data and exploiting both spatial, temporal, and multimodal links between corresponding 2D and 3D regions. The proposed method was evaluated on a diverse data set, comprising a dairy paddock and different orchards gathered with a perception research robot in Australia. Results showed that for a two‐class classification problem (ground and nonground), only the camera leveraged from information provided by the other modality with an increase in the mean classification score of 0.5%. However, as more classes were introduced (ground, sky, vegetation, and object), both modalities complemented each other with improvements of 1.4% in 2D and 7.9% in 3D. Finally, introducing temporal links between successive frames resulted in improvements of 0.2% in 2D and 1.5% in 3D.     

Dyna-Q-based vector direction for path planning problem of autonomous mobile robots in unknown environments

Reinforcement learning (RL) is a popular method for solving the path planning problem of autonomous mobile robots in unknown environments. However, the primary difficulty faced by learning robots using the RL method is that they learn too slowly in obstacle-dense environments. To more efficiently solve the path planning problem of autonomous mobile robots in such environments, this paper presents a novel approach in which the robot’s learning process is divided into two phases. The first one is to accelerate the learning process for obtaining an optimal policy by developing the well-known Dyna-Q algorithm that trains the robot in learning actions for avoiding obstacles when following the vector direction. In this phase, the robot’s position is represented as a uniform grid. At each time step, the robot performs an action to move to one of its eight adjacent cells, so the path obtained from the optimal policy may be longer than the true shortest path. The second one is to train the robot in learning a collision-free smooth path for decreasing the number of the heading changes of the robot. The simulation results show that the proposed approach is efficient for the path planning problem of autonomous mobile robots in unknown environments with dense obstacles.     

A robust online path planning approach in cluttered environments for micro rotorcraft drones

We present in this paper a robust online path planning method, which allows a micro rotorcraft drone to fly safely in GPS-denied and obstacle-strewn environments with limited onboard computational power. The approach is based on an efficiently managed grid map and a closed-form solution to the two point boundary value problem (TPBVP). The grid map assists trajectory evaluation whereas the solution to the TPBVP generates smooth trajectories. Finally, a top-level trajectory switching algorithm is utilized to minimize the computational cost. Advantages of the proposed approach include its conservation of computational resource, robustness of trajectory generation and agility of reaction to unknown environment. The result has been realized on actual drones platforms and successfully demonstrated in real flight tests. The video of flight tests can be found at: http://uav.ece.nus.edu.sg/robust-online-path-planning-Lai2015.html.     

激光—相机系统语义栅格建图和路径规划

目的 SLAM（simultaneous localization and mapping）是移动机器人在未知环境进行探索、感知和导航的关键技术。激光SLAM测量精确，便于机器人导航和路径规划，但缺乏语义信息。而视觉SLAM的图像能提供丰富的语义信息，特征区分度更高，但其构建的地图不能直接用于路径规划和导航。为了实现移动机器人构建语义地图并在地图上进行路径规划，本文提出一种语义栅格建图方法。方法 建立可同步获取激光和语义数据的激光-相机系统，将采集的激光分割数据与目标检测算法获得的物体包围盒进行匹配，得到各物体对应的语义激光分割数据。将连续多帧语义激光分割数据同步融入占据栅格地图。对具有不同语义类别的栅格进行聚类，得到标注物体类别和轮廓的语义栅格地图。此外，针对语义栅格地图发布导航任务，利用路径搜索算法进行路径规划，并对其进行改进。结果 在实验室走廊和办公室分别进行了语义栅格建图的实验，并与原始栅格地图进行了比较。在语义栅格地图的基础上进行了路径规划，并采用了语义赋权算法对易移动物体的路径进行对比。结论 多种环境下的实验表明本文方法能获得与真实环境一致性较高、标注环境中物体类别和轮廓的语义栅格地图，且实验硬件结构简单、成本低、性能良好，适用于智能化机器人的导航和路径规划。     

面向自动驾驶目标检测的深度多模态融合技术

研究者关注利用多个传感器来提升自动驾驶中目标检测模型的准确率,因此对目标检测中的数据融合方法进行研究具有重要的学术和应用价值。为此,本文总结了近年来自动驾驶中深度目标检测模型中的数据融合方法。首先介绍了自动驾驶中深度目标检测技术和数据融合技术的发展,以及已有的研究综述;接着从多模态目标检测、数据融合的层次、数据融合的计算方法3个方面展开阐述,全面展现了该领域的前沿进展;此外,本文提出了数据融合的合理性分析,从方法、鲁棒性、冗余性3个角度对数据融合方法进行了讨论;最后讨论了融合方法的一些公开问题,并从挑战、策略和前景等方面作了总结。