Playing Flappy Bird Based on Motion Recognition Using a Transformer Model and LIDAR Sensor.

A transformer neural network is employed in the present study to predict Q-values in a simulated environment using reinforcement learning techniques. The goal is to teach an agent to navigate and excel in the Flappy Bird game, which became a popular model for control in machine learning approaches. Unlike most top existing approaches that use the game's rendered image as input, our main contribution lies in using sensory input from LIDAR, which is represented by the ray casting method. Specifically, we focus on understanding the temporal context of measurements from a ray casting perspective and optimizing potentially risky behavior by considering the degree of the approach to objects identified as obstacles. The agent learned to use the measurements from ray casting to avoid collisions with obstacles. Our model substantially outperforms related approaches. Going forward, we aim to apply this approach in real-world scenarios.

Signal Novelty Detection as an Intrinsic Reward for Robotics.

In advanced robot control, reinforcement learning is a common technique used to transform sensor data into signals for actuators, based on feedback from the robot's environment. However, the feedback or reward is typically sparse, as it is provided mainly after the task's completion or failure, leading to slow convergence. Additional intrinsic rewards based on the state visitation frequency can provide more feedback. In this study, an Autoencoder deep learning neural network was utilized as novelty detection for intrinsic rewards to guide the search process through a state space. The neural network processed signals from various types of sensors simultaneously. It was tested on simulated robotic agents in a benchmark set of classic control OpenAI Gym test environments (including Mountain Car, Acrobot, CartPole, and LunarLander), achieving more efficient and accurate robot control in three of the four tasks (with only slight degradation in the Lunar Lander task) when purely intrinsic rewards were used compared to standard extrinsic rewards. By incorporating autoencoder-based intrinsic rewards, robots could potentially become more dependable in autonomous operations like space or underwater exploration or during natural disaster response. This is because the system could better adapt to changing environments or unexpected situations.

Wearable Sensor-Based Human Activity Recognition with Transformer Model.

Computing devices that can recognize various human activities or movements can be used to assist people in healthcare, sports, or human-robot interaction. Readily available data for this purpose can be obtained from the accelerometer and the gyroscope built into everyday smartphones. Effective classification of real-time activity data is, therefore, actively pursued using various machine learning methods. In this study, the transformer model, a deep learning neural network model developed primarily for the natural language processing and vision tasks, was adapted for a time-series analysis of motion signals. The self-attention mechanism inherent in the transformer, which expresses individual dependencies between signal values within a time series, can match the performance of state-of-the-art convolutional neural networks with long short-term memory. The performance of the proposed adapted transformer method was tested on the largest available public dataset of smartphone motion sensor data covering a wide range of activities, and obtained an average identification accuracy of 99.2% as compared with 89.67% achieved on the same data by a conventional machine learning method. The results suggest the expected future relevance of the transformer model for human activity recognition.