Cheng Zhou

Lei Han, Qingxu Zhu, Jiapeng Sheng et al.

Knowledge from animals and humans inspires robotic innovations. Numerous efforts have been made to achieve agile locomotion in quadrupedal robots through classical controllers or reinforcement learning approaches. These methods usually rely on physical models or handcrafted rewards to accurately describe the specific system, rather than on a generalized understanding like animals do. Here we propose a hierarchical framework to construct primitive-, environmental- and strategic-level knowledge that are all pre-trainable, reusable and enrichable for legged robots. The primitive module summarizes knowledge from animal motion data, where, inspired by large pre-trained models in language and image understanding, we introduce deep generative models to produce motor control signals stimulating legged robots to act like real animals. Then, we shape various traversing capabilities at a higher level to align with the environment by reusing the primitive module. Finally, a strategic module is trained focusing on complex downstream tasks by reusing the knowledge from previous levels. We apply the trained hierarchical controllers to the MAX robot, a quadrupedal robot developed in-house, to mimic animals, traverse complex obstacles and play in a designed challenging multi-agent chase tag game, where lifelike agility and strategy emerge in the robots.

Jiawei Xu, Cheng Zhou, Yizheng Zhang et al.

We consider the problem of policy transfer between two Markov Decision Processes (MDPs). We introduce a lemma based on existing theoretical results in reinforcement learning to measure the relativity gap between two arbitrary MDPs, that is the difference between any two cumulative expected returns defined on different policies and environment dynamics. Based on this lemma, we propose two new algorithms referred to as Relative Policy Optimization (RPO) and Relative Transition Optimization (RTO), which offer fast policy transfer and dynamics modelling, respectively. RPO transfers the policy evaluated in one environment to maximize the return in another, while RTO updates the parameterized dynamics model to reduce the gap between the dynamics of the two environments. Integrating the two algorithms results in the complete Relative Policy-Transition Optimization (RPTO) algorithm, in which the policy interacts with the two environments simultaneously, such that data collections from two environments, policy and transition updates are completed in one closed loop to form a principled learning framework for policy transfer. We demonstrate the effectiveness of RPTO on a set of MuJoCo continuous control tasks by creating policy transfer problems via variant dynamics.

Rui Zhao, Xihui Li, Yizheng Zhang et al.

Multi-agent deep Reinforcement Learning (RL) has made significant progress in developing intelligent game-playing agents in recent years. However, the efficient training of collective robots using multi-agent RL and the transfer of learned policies to real-world applications remain open research questions. In this work, we first develop a comprehensive robotic system, including simulation, distributed learning framework, and physical robot components. We then propose and evaluate reinforcement learning techniques designed for efficient training of cooperative and competitive policies on this platform. To address the challenges of multi-agent sim-to-real transfer, we introduce Out of Distribution State Initialization (OODSI) to mitigate the impact of the sim-to-real gap. In the experiments, OODSI improves the Sim2Real performance by 20%. We demonstrate the effectiveness of our approach through experiments with a multi-robot car competitive game and a cooperative task in real-world settings.

Wentao Gao, Cheng Zhou

Accurate prediction of human behavior is crucial for effective human-robot interaction (HRI) systems, especially in dynamic environments where real-time decisions are essential. This paper addresses the challenge of forecasting future human behavior using multivariate time series data from wearable sensors, which capture various aspects of human movement. The presence of hidden confounding factors in this data often leads to biased predictions, limiting the reliability of traditional models. To overcome this, we propose a robust predictive model that integrates deconfounding techniques with advanced time series prediction methods, enhancing the model's ability to isolate true causal relationships and improve prediction accuracy. Evaluation on real-world datasets demonstrates that our approach significantly outperforms traditional methods, providing a more reliable foundation for responsive and adaptive HRI systems.

Yingtian Tang, Jiangtao Liu, Cheng Zhou et al.

Motion style transfer is highly desired for motion generation systems for gaming. Compared to its offline counterpart, the research on online motion style transfer under interactive control is limited. In this work, we propose an end-to-end neural network that can generate motions with different styles and transfer motion styles in real-time under user control. Our approach eliminates the use of handcrafted phase features, and could be easily trained and directly deployed in game systems. In the experiment part, we evaluate our approach from three aspects that are essential for industrial game design: accuracy, flexibility, and variety, and our model performs a satisfying result.

Mingjie Li, Youqian Feng, Zhonghai Yin et al.

The traditional methods of action recognition are not specific for the operator, thus results are easy to be disturbed when other actions are operated in videos. The network based on mixed convolutional resnet and RPN is proposed in this paper. The rMC is tested in the data set of UCF-101 to compare with the method of R3D. The result shows that its correct rate reaches 71.07%. Meanwhile, the action recognition network is tested in our gesture and body posture data sets for specific target. The simulation achieves a good performance in which the running speed reaches 200 FPS. Finally, our model is improved by introducing the regression block and performs better, which shows the great potential of this model.

Mingjie Li, Youqian Feng, Zhonghai Yin et al.

Common target detection is usually based on single frame images, which is vulnerable to affected by the similar targets in the image and not applicable to video images. In this paper , anchor mask is proposed to add the prior knowledge for target detection and an anchor mask net is designed to impove the RPN performance for single target detection. Tested in the VOT2016, the model perform better.

Cheng Zhou, Fang Han, Xinsheng Zhang et al.

There has been an increasing interest in testing the equality of large Pearson's correlation matrices. However, in many applications it is more important to test the equality of large rank-based correlation matrices since they are more robust to outliers and nonlinearity. Unlike the Pearson's case, testing the equality of large rank-based statistics has not been well explored and requires us to develop new methods and theory. In this paper, we provide a framework for testing the equality of two large U-statistic based correlation matrices, which include the rank-based correlation matrices as special cases. Our approach exploits extreme value statistics and the Jackknife estimator for uncertainty assessment and is valid under a fully nonparametric model. Theoretically, we develop a theory for testing the equality of U-statistic based correlation matrices. We then apply this theory to study the problem of testing large Kendall's tau correlation matrices and demonstrate its optimality. For proving this optimality, a novel construction of least favourable distributions is developed for the correlation matrix comparison.