Abstract. Controlling a biped robot with a high degree of freedom to achieve stable and straight movement patterns is a complex problem. With growing computational power of computer hardware, high resolution real time simulation of such robot models has become more and more applicable. This paper presents a novel approach to generate bipedal gait for humanoid locomotion. This approach is based on modified Truncated Fourier Series (TFS) for generating angular trajectories. It is also the first time that Particle Swarm Optimization (PSO) is used to find the best angular trajectory and optimize TFS. This method has been implemented on Simulated NAO robot in Robocup 3D soccer simulation environment (rcssserver3d). To overcome inherent noise of the simulator we applied a Resampling algorithm which could lead the robustness in nondeterministic environments. Experimental results show that PSO optimizes TFS faster and better than GA to generate straighter and faster humanoid locomotion.

No abstract

No abstract

Engagement is a key indicator of the quality of learning experience, and one that plays a major role in developing intelligent educational interfaces. Any such interface requires the ability to recognise the level of engagement in order to respond appropriately; however, there is very little existing data to learn from, and new data is expensive and difficult to acquire. This paper presents a deep learning model to improve engagement recognition from images that overcomes the data sparsity challenge by pre-training on readily available basic facial expression data, before training on specialised engagement data. In the first of two steps, a facial expression recognition model is trained to provide a rich face representation using deep learning. In the second step, we use the model's weights to initialize our deep learning based model to recognize engagement; we term this the engagement model. We train the model on our new engagement recognition dataset with 4627 engaged and disengaged samples. We find that the engagement model outperforms effective deep learning architectures that we apply for the first time to engagement recognition, as well as approaches using histogram of oriented gradients and support vector machines.

No abstract