This work is supported by the National Natural Science Foundation of China (61672437, 61702428, 61702383, 61972324), the New Generation Artificial Intelligence Science and Technology Major Project of Sichuan Province (2018GZDZX0043) and the Sichuan Science and Technology Program (2018GZ0185, 2018GZ0086, 2018GZ0095), Funded by Beijing Advanced Innovation Center for Intelligent Robots and Systems (2019IRS14), Artificial Intelligence Key Laboratory of Sichuan Province (2019RYJ06), Subproject of the National Key Research and Development Program of China (2017YFD0401102-02), Key Project of Philosophy and Social Science Research Project of Hubei Provincial Department of Education in 2019 (19D59), Science and Technology Research Project of Hubei Department of Education (D20191604).