Search

Environmental information plays an important role in deep reinforcement learning (DRL). However, many algorithms do not pay much attention to environmental information. In multi-agent reinforcement learning decision-making, because agents need to make decisions combined with the information of other agents in the environment, this makes the environmental information more important. To prove the importance of environmental information, we added environmental information to the algorithm. We evaluated many algorithms on a challenging set of StarCraft II micromanagement tasks. Compared with the original algorithm, the standard deviation (except for the VDN algorithm) was smaller than that of the original algorithm, which shows that our algorithm has better stability. The average score of our algorithm was higher than that of the original algorithm (except for VDN and COMA), which shows that our work significantly outperforms existing multi-agent RL methods. [ABSTRACT FROM AUTHOR]

Planar surfaces are prevalent components of man-made indoor scenes, and plane extraction plays a vital role in practical applications of computer vision and robotics, such as scene understanding, and mobile manipulation. Nowadays, most plane extraction methods are based on reconstruction of the scene. In this paper, plane representation is formulated in inverse-depth images. Based on this representation, we explored the potential to extract planes in images directly. A fast plane extraction approach, which employs the region growing algorithm in inverse-depth images, is presented. This approach consists of two main components: seeding, and region growing. In the seeding component, seeds are carefully selected locally in grid cells to improve exploration efficiency. After seeding, each seed begins to grow into a continuous plane in succession. Both greedy policy and a normal coherence check are employed to find boundaries accurately. During growth, neighbor coplanar planes are checked and merged to overcome the over-segmentation problem. Through experiments on public datasets and generated saw-tooth images, the proposed approach achieves 80.2% CDR (Correct Detection Rate) on the ABW SegComp Dataset, which has proven that it has comparable performance with the state-of-the-art. The proposed approach runs at 5 Hz on typical 680 × 480 images, which has shown its potential in real-time practical applications in computer vision and robotics with further improvement. [ABSTRACT FROM AUTHOR]

Random forest-based methods for 3D temporal tracking over an image sequence have gained increasing prominence in recent years. They do not require object's texture and only use the raw depth images and previous pose as input, which makes them especially suitable for textureless objects. These methods learn a built-in occlusion handling from predetermined occlusion patterns, which are not always able to model the real case. Besides, the input of random forest is mixed with more and more outliers as the occlusion deepens. In this paper, we propose an occlusion-aware framework capable of real-time and robust 3D pose tracking from RGB-D images. To this end, the proposed framework is anchored in the random forest-based learning strategy, referred to as RFtracker. We aim to enhance its performance from two aspects: integrated local refinement of random forest on one side, and online rendering based occlusion handling on the other. In order to eliminate the inconsistency between learning and prediction of RFtracker, a local refinement step is embedded to guide random forest towards the optimal regression. Furthermore, we present an online rendering-based occlusion handling to improve the robustness against dynamic occlusion. Meanwhile, a lightweight convolutional neural network-based motion-compensated (CMC) module is designed to cope with fast motion and inevitable physical delay caused by imaging frequency and data transmission. Finally, experiments show that our proposed framework can cope better with heavily-occluded scenes than RFtracker and preserve the real-time performance.