Ahmad Terra's scientific contributions

Publications (7)

Article
Full-text available
Deep Reinforcement Learning (RL) is a black-box method and is hard to understand because the agent employs a neural network (NN). To explain the behavior and decisions made by the agent, different eXplainable RL (XRL) methods are developed; for example, feature importance methods are applied to analyze the contribution of the input side of the mode...
Preprint
Full-text available
The number of mobile robots with constrained computing resources that need to execute complex machine learning models has been increasing during the past decade. Commonly, these robots rely on edge infrastructure accessible over wireless communication to execute heavy computational complex tasks. However, the edge might become unavailable and, cons...

Citations

... Wang et al. [15] highlighted the importance of the baseline data that are required for the SHAP method in the RL problem but did not provide a detailed data selection method nor its verification. For a machine learning problem, SHAP [4] is a model-agnostic method in which it is observed to produce the best results when applied to the telecommunications use case [16]. RL-SHAP [17] is an example where SHAP [4] can be applied to the RL problem to explain the contribution of the actor's input features. ...
... Environment understanding, as the name implies, means that the inspection robot captures information about the robot's surroundings using its own configured sensors and effectively preprocesses and fuses this data through relevant algorithms to construct a mathematical model of the deep semantic features of the environment [12]. Finally, it generates a graph from sensor data to represent the relationship between the detected objects [13,14]. Its own configured sensors are mainly ultrasonic radar sensors, LiDAR sensors, and visible light sensors. ...
... Safety insurance owns the highest priority during manufacturing operations. To achieve safety control in human-robot interaction (HRI), DRL is mainly used to generate collision avoidance motion planning or navigation control strategies (Xiong et al. [255], Zhu et al. [256], Liu et al. [257], Terra et al. [258]) for industrial robot arms or AGVs. ...