Search

Manipulating objects without grasping them enables more complex tasks, known as non-prehensile manipulation. Most previous methods only learn one manipulation skill, such as reach or push, and cannot achieve flexible object manipulation.In this work, we introduce MRLM, a Multi-stage Reinforcement Learning approach for non-prehensile Manipulation of objects.MRLM divides the task into multiple stages according to the switching of object poses and contact points.At each stage, the policy takes the point cloud-based state-goal fusion representation as input, and proposes a spatially-continuous action that including the motion of the parallel gripper pose and opening width.To fully unlock the potential of MRLM, we propose a set of technical contributions including the state-goal fusion representation, spatially-reachable distance metric, and automatic buffer compaction.We evaluate MRLM on an Occluded Grasping task which aims to grasp the object in configurations that are initially occluded.Compared with the baselines, the proposed technical contributions improve the success rate by at least 40\% and maximum 100\%, and avoids falling into local optimum.Our method demonstrates strong generalization to unseen object with shapes outside the training distribution.Moreover, MRLM can be transferred to real world with zero-shot transfer, achieving a 95\% success rate.Code and videos can be found at https://sites.google.com/view/mrlm.

Driver gaze zone estimation is an important task in Advanced Driver Assistance Systems (ADAS), which suffers difficulties including head pose, capture direction, glass occlusion, and real-time requirement, etc. Most previous methods combine face modalities and head pose using concat process, which may result in over-fitting due to the unbalanced dimension. Focusing on gaze zone estimation problems, we propose the Head Pose Fusion Assisted supervision & Eye Region Weighted Encoding (HP-ERW) structure, which fuses head pose attribute and face modalities together through spatial attention and Kronecker product mechanisms. Firstly, we introduce a pre-processing module dealing with head pose and face information, with the purpose of extracting input vectors and improving the fusion speed of the HP-ERW structure. Secondly, an Eye Region Weighted Encoding Network (ERW-Net) based on spatial attention is proposed to strengthen the networks perception ability for encoding features. Finally, we propose a dual-channel Head Pose Fusion Network (HP-Net) based on the Kronecker product mechanism, with the purpose of fusing head pose and improving the estimation accuracy. Experiments show that the HP-ERW outperforms compared existing methods on several public datasets. The designed ADAS using the proposed method achieves 23.5 fps real-time application with small memory requirement of 4,884 KB.

Grasp detection in cluttered scenes is a very challenging task for robots. Generating synthetic grasping data is a popular way to train and test grasp methods, as is Dex-net and GraspNet; yet, these methods generate training grasps on 3D synthetic object models, but evaluate at images or point clouds with different distributions, which reduces performance on real scenes due to sparse grasp labels and covariate shift. To solve existing problems, we propose a novel on-policy grasp detection method, which can train and test on the same distribution with dense pixel-level grasp labels generated on RGB-D images. A Parallel-Depth Grasp Generation (PDG-Generation) method is proposed to generate a parallel depth image through a new imaging model of projecting points in parallel; then this method generates multiple candidate grasps for each pixel and obtains robust grasps through flatness detection, force-closure metric and collision detection. Then, a large comprehensive Pixel-Level Grasp Pose Dataset (PLGP-Dataset) is constructed and released; distinguished with previous datasets with off-policy data and sparse grasp samples, this dataset is the first pixel-level grasp dataset, with the on-policy distribution where grasps are generated based on depth images. Lastly, we build and test a series of pixel-level grasp detection networks with a data augmentation process for imbalance training, which learn grasp poses in a decoupled manner on the input RGB-D images. Extensive experiments show that our on-policy grasp method can largely overcome the gap between simulation and reality, and achieves the state-of-the-art performance. Code and data are provided at https://github.com/liuchunsense/PLGP-Dataset., The experiment had design flaws

With the advantage of high maneuverability, Unmanned Aerial Vehicles (UAVs) have been widely deployed in vehicle monitoring and controlling. However, processing the images captured by UAV for the extracting vehicle information is hindered by some challenges including arbitrary orientations, huge scale variations and partial occlusion. In seeking to address these challenges, we propose a novel Multi-Scale and Occlusion Aware Network (MSOA-Net) for UAV based vehicle segmentation, which consists of two parts including a Multi-Scale Feature Adaptive Fusion Network (MSFAF-Net) and a Regional Attention based Triple Head Network (RATH-Net). In MSFAF-Net, a self-adaptive feature fusion module is proposed, which can adaptively aggregate hierarchical feature maps from multiple levels to help Feature Pyramid Network (FPN) deal with the scale change of vehicles. The RATH-Net with a self-attention mechanism is proposed to guide the location-sensitive sub-networks to enhance the vehicle of interest and suppress background noise caused by occlusions. In this study, we release a large comprehensive UAV based vehicle segmentation dataset (UVSD), which is the first public dataset for UAV based vehicle detection and segmentation. Experiments are conducted on the challenging UVSD dataset. Experimental results show that the proposed method is efficient in detecting and segmenting vehicles, and outperforms the compared state-of-the-art works.

Occlusions, complex backgrounds, scale variations and non-uniform distributions present great challenges for crowd counting in practical applications. In this paper, we propose a novel method using an attention model to exploit head locations which are the most important cue for crowd counting. The attention model estimates a probability map in which high probabilities indicate locations where heads are likely to be present. The estimated probability map is used to suppress non-head regions in feature maps from several multi-scale feature extraction branches of a convolution neural network for crowd density estimation, which makes our method robust to complex backgrounds, scale variations and non-uniform distributions. In addition, we introduce a relative deviation loss to compensate a commonly used training loss, Euclidean distance, to improve the accuracy of sparse crowd density estimation. Experiments on Shanghai-Tech, UCF_CC_50 and World-Expo'10 data sets demonstrate the effectiveness of our method.