This paper presents the use of two popular explainability tools called Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP) to explain the predictions made by a trained deep neural network. The deep neural network used in this work is trained on the UCI Breast Cancer Wisconsin dataset. The neural network is used to classify the masses found in patients as benign or malignant based on 30 features that describe the mass. LIME and SHAP are then used to explain the individual predictions made by the trained neural network model. The explanations provide further insights into the relationship between the input features and the predictions. SHAP methodology additionally provides a more holistic view of the effect of the inputs on the output predictions. The results also present the commonalities between the insights gained using LIME and SHAP. Although this paper focuses on the use of deep neural networks trained on UCI Breast Cancer Wisconsin dataset, the methodology can be applied to other neural networks and architectures trained on other applications. The deep neural network trained in this work provides a high level of accuracy. Analyzing the model using LIME and SHAP adds the much desired benefit of providing explanations for the recommendations made by the trained model.

Summary: This paper introduces an approach of collaborative control for individual robots to collaboratively perform a common task, without the need for a centralized controller to coordinate the group. The approach is illustrated by an application example involving multiple robots performing a collaborative task to achieve a common goal. The objective of this example problem is to control multiple robots that are connected to an object through elastic cables in order to bring the object to a target position. There is no communication between the robots, and hence each robot is unaware of how the other robots are going to react at any instant. Only the information pertaining to the object and the target is available to all the robots at any instant. Genetic fuzzy system (GFS) is used to develop controller for each of the robots. The nonlinearity of fuzzy logic systems coupled with the search capability of genetic algorithms provides a tool to design controllers for such collaborative tasks. A set of training scenarios are developed to train the individual robot controllers for this task. The trained controllers are then tested on an extensive set of scenarios. This paper describes the development process of GFS controllers for dynamic case involving systems consisting of three robots. It is also shown that the GFS controllers are scalable for the more complex systems involving more than three robots.

In this work, we train controllers (models) using Genetic Fuzzy Methodology (GFM) for learning cooperative behavior in a team of decentralized UAVs to transport a shared slung payload. The training is done in a reinforcement learning fashion where the models learn strategies based on feedback received from the environment. The controllers in the UAVs are modeled as fuzzy systems. Genetic Algorithm is used to evolve the models to achieve the overall goal of bringing the payload to the desired locations while satisfying the physical and operational constraints. The UAVs do not explicitly communicate with one another, and each UAV makes its own decisions, thus making it a decentralized system. However, during the training, the cost function is defined such that it is a representation of the team’s effectiveness in achieving the overall goal of bringing the shared payload to the target. By including a penalization term for any constraint violation during the training, the UAVs learn strategies that do not require explicit communication to achieve efficient transportation of payload while satisfying all constraints. We also present the performance metrics by testing the trained UAVs on new scenarios with different target locations and with different number of UAVs in the team.

Fuzzy logic is used in a variety of applications due to its universal approximator attribute and non-linear characteristics. The tuning of the parameters of a fuzzy logic system, viz. the membership functions and the rulebase, requires a lot of trial and error. This process could be simplified by using a heuristic search algorithm like genetic algorithm (GA). In this chapter, we discuss the design of such a genetic fuzzy controller that can control an inverted double pendulum. GA improves the fuzzy logic controller (FLC) with each generation during the training process to obtain an FLC that can bring the pendulum to its inverted position. After training, the effectiveness of the FLC is tested for different scenarios by varying the initial conditions. We also show the effectiveness of the FLC even when subjected to noise and how the performance improves when the controller is tuned with noise.