DSDongqing Shi

Dongqing Shi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dongqing Shi has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Hierarchical Computational Model Inspired by the Behavioral Control in the Primate Brain

    by Dongqing Shi, Jerald Kralik, Haiyan Mi

    The basic cognitive architecture of our brain is still unknown. However, scientists have found evidence for existence of distinct behavioral control systems shared by humans and nonhumans. Inspired by the problem solving systems of the behavioral control in the primate brain, a hierarchical computational model is presented. We focus on the integrative performance of brain substructures, each of which is represented by a problem solver that is further modeled by a certain algorithm. Different levels of brain substructures, as well as the corresponding algorithms, are hierarchically organized both in structure and in function, including how and when higher-order solvers control lower-order ones. Different problem solvers share a same slice of working memory. This novelty is claimed since most of existing brain models emphasize on the neural network structure even though the neuron dynamics of brain is still very controversial. And we compare its performance to three other computational models in the face of a challenging foraging problem. Agents are examined in foraging environment with different sizes, and/or transparent barriers. The experimental results show that our model performed the best outright in most scenarios. Further, the results discover that the virtues of our primate brain lie not only in the heights of thinking it can reach, but also in its range and versatility.


  • Open Access

    An Indoor Low-Cost and High-Accuracy Localization Approach for AGVs

    by Dongqing Shi, Haiyan Mi, Emmanuel G. Collins, Jun Wu

    Demanding for warehousing automation and intelligence is critical with the rapid development of information and big data teleology. In most storehouses, cargos are mainly carried by Automatic Guided Vehicles (AGVs) or even manpower. Most AGVs follow predefined paths that are normally paved by some marks detected by AGVs. It largely limits the application of AGVs. Some AGVs relies on highly accurate Light Laser Detection and Ranging (LiDAR) devices for navigation. The paper presents a low-cost localization approach for indoor AGVs with the localization accuracy up to centimetres. The proposed method not only allows an AGV to move precisely without any predefined paths, but also reduces the cost largely. The Ultra Wide Band (UWB) technology is used in our approach. In the paper, a gradient decent method cooperated with a least square method is developed to deal with the nonlinearity of UWB ranging data. An optimal localization result is achieved within a small amount of iterations. The positioning results are also compared to a high-accuracy Real-Time Kinematic (RTK) satellite system. Meanwhile, the approach is able to diagnose the original UWB data and will discard any data corrupted by non-ignorable noises. Thus, the robustness is guaranteed.


  • Design of a Flyback Switching Power for Smart Meter

    by Fan Jian-Ying, Zhang Yu-Ling, Shi Dong-Qing

  • Multi-agent reinforcement learning and chimpanzee hunting

    by Michael Z. Sauter, Dongqing Shi, Jerald D. Kralik

    The use of multi-agent reinforcement learning is growing because of it's ability to scale in complexity and its lack of need for knowledge of the state and other agents. Chimpanzee hunting behavior is a suitable complex and interesting model for which multi-agent reinforcement learning is appropriate. Chimpanzee hunting strategies vary in both use and complexity and ultimately depend on the environment for which they are applied. Learning to use the varying strategies and learning when they are most effective is what this paper addresses and provides initial results and framework to build upon.