For CNNs based stereo matching methods, cost volumes play an important role in achieving good matching accuracy. In this paper, we present an end-to-end trainable convolution neural network to fully use cost volumes for stereo matching. Our network consists of three sub-modules, i.e., shared feature extraction, initial disparity estimation, and disparity refinement. These sub-modules of our network are tightly-coupled, making it compact and easy to train. Moreover, we investigate the problem of developing a robust model to perform well across multiple datasets with different characteristics. We achieve this by introducing a two-stage finetuning scheme to gently transfer the model to target datasets. Specifically, in the first stage, the model is finetuned using both a large synthetic dataset and the target datasets with a relatively large learning rate, while in the second stage the model is trained using only the target datasets with a small learning rate. The proposed method is tested on several benchmarks including the Middlebury 2014, KITTI 2015, ETH3D 2017, and SceneFlow datasets. Experimental results show that our method achieves the state-of-the-art performance on all the datasets. The proposed method also won the 1st prize on the Stereo task of Robust Vision Challenge 2018.

Coverage path planning (CPP) of multiple Dubins robots has been extensively applied in aerial monitoring, marine exploration, and search and rescue. Existing multi-robot coverage path planning (MCPP) research use exact or heuristic algorithms to address coverage applications. However, several exact algorithms always provide precise area division rather than coverage paths, and heuristic methods face the challenge of balancing accuracy and complexity. This paper focuses on the Dubins MCPP problem of known environments. Firstly, we present an exact Dubins multi-robot coverage path planning (EDM) algorithm based on mixed linear integer programming (MILP). The EDM algorithm searches the entire solution space to obtain the shortest Dubins coverage path. Secondly, a heuristic approximate credit-based Dubins multi-robot coverage path planning (CDM) algorithm is presented, which utilizes the credit model to balance tasks among robots and a tree partition strategy to reduce complexity. Comparison experiments with other exact and approximate algorithms demonstrate that EDM provides the least coverage time in small scenes, and CDM produces a shorter coverage time and less computation time in large scenes. Feasibility experiments demonstrate the applicability of EDM and CDM to a high-fidelity fixed-wing unmanned aerial vehicle (UAV) model.

Energy efficient architecture is essential to improve both the performance and power consumption of a computer system. However, modern computers suffer from the severe “memory wall” problem due to the significant performance gap between the processor technology and the memory technology. Thus, the computer architecture community is evolving from compute-centric to memory-centric designs to reduce the data movement overhead. This paper presents a comprehensive survey of the main challenges and recent advances in memory-centric energy efficient computer architecture. We summarize two research directions: improving the memory technology and processing closer to memory. The former focuses on optimizing the conventional memory technology and exploiting emerging non-volatile memory (NVM) technology. The latter talks about currently popular processing in memory (PIM) technology, including near-memory processing (NMP) and in-memory processing (IMP). Moreover, some other topics like hardware for machine learning (ML), ML for hardware, security, privacy, and reliability are gaining increasing attention and should be considered seriously in the design phase of a computer system. The community is facing various challenges and opportunities simultaneously, requiring researchers to have a more comprehensive understanding of this field which is also the goal of this paper.

Conventional Coordinate Rotation Digital Computer (CORDIC) algorithm is an effective implementation of trigonometric function, and it has been widely applied in digital signal processing. In this paper, we propose a novel CORDIC architecture based on Scaling Free (SF) theory, which adopts adaptive recoding method to reduce the iterations and eliminate the scaling factor. The proposed scheme has been synthesized using 65nm CMOS technology with standard cell library. Compared with SFB4C, our scheme saves 21.11% to 34.64% hardware-overhead with no performance penalty. © IEICE 2012.

CGRA (Coarse-Grained Reconfigurable Array) is competitive hardware architecture for streaming applications due to its excellent tradeoff between programmability and efficiency. However, the efficiency of CGRA highly depends on how applications are mapped onto it with optimized operation placement and data routing. In the routing procedure, data are transferred through different processing elements by occupying the data path so that reduce hardware consumed by routing is important. This paper presents a 2-step ant colony algorithm for the route resource sharing optimization to obtain better data transfer path for CGRA application mapping, which can be modeled as a Steiner Tree problem. By dividing the searching procedure of ants into two steps, the execution time of proposed method was 32% less than the traditional ant colony algorithm. Meanwhile, the quality of result only deteriorates 0.4%. Compared to the simple heuristic method MPH, the optimized ant colony algorithm shortens the length of data transfer path by 4-6%.