Search results

The aim of this article is two-fold. First, it offers a unique account of San Min, the prototype of the current Chinese educational principle proposed by Yan Fu (1854–1921) that aimed at improving people’s physical, intellectual and moral capacities. This system of educational thinking has received only marginal attention in Anglophone research literature. Second, given the influence of Yan Fu’s interpretation and promulgation of Herbert Spencer’s educational philosophy during that period, it investigates the extent to which San Min is derived from Spencer’s educational thought (the “Spencerian Triad”). This article focusses on how Yan Fu adapted the ideas of San Min from Spencer’s account.

This article considers Yan Fu’s principle of San Min in relation to Spencer’s educational triad through a close reading and comparison of key primary texts (including Yan Fu’s original writing). It explores the similarities and differences between each account of education’s goals and its proposed means of attainment.

Yan Fu’s principle of San Min is shown to have been adapted from the Spencerian Triad. However, using the theory of Social Organism, Yan Fu re-interpreted Spencer’s individual liberty as liberty for the nation. While Spencer’s goal was to empower individuals, Yan Fu aimed to serve collective independence, wealth and power.

This article addresses oversights concerning San Min’s Western origins in the Spencerian Triad and its influence on Chinese education under Yan Fu’s sway. It is significant because San Min is still at the core of the current Chinese educational policy.

Limited by the types of sensors, the state information available for musculoskeletal robots with highly redundant, nonlinear muscles is often incomplete, which makes the control face a bottleneck problem. The aim of this paper is to design a method to improve the motion performance of musculoskeletal robots in partially observable scenarios, and to leverage the ontology knowledge to enhance the algorithm’s adaptability to musculoskeletal robots that have undergone changes.

A memory and attention-based reinforcement learning method is proposed for musculoskeletal robots with prior knowledge of muscle synergies. First, to deal with partially observed states available to musculoskeletal robots, a memory and attention-based network architecture is proposed for inferring more sufficient and intrinsic states. Second, inspired by muscle synergy hypothesis in neuroscience, prior knowledge of a musculoskeletal robot’s muscle synergies is embedded in network structure and reward shaping.

Based on systematic validation, it is found that the proposed method demonstrates superiority over the traditional twin delayed deep deterministic policy gradients (TD3) algorithm. A musculoskeletal robot with highly redundant, nonlinear muscles is adopted to implement goal-directed tasks. In the case of 21-dimensional states, the learning efficiency and accuracy are significantly improved compared with the traditional TD3 algorithm; in the case of 13-dimensional states without velocities and information from the end effector, the traditional TD3 is unable to complete the reaching tasks, while the proposed method breaks through this bottleneck problem.

In this paper, a novel memory and attention-based reinforcement learning method with prior knowledge of muscle synergies is proposed for musculoskeletal robots to deal with partially observable scenarios. Compared with the existing methods, the proposed method effectively improves the performance. Furthermore, this paper promotes the fusion of neuroscience and robotics.