Ian Showalter

Bio: Ian Showalter is an academic researcher from Carleton University. The author has contributed to research in topics: Artificial neural network & Evolutionary computation. The author has an hindex of 4, co-authored 8 publications receiving 26 citations.

Neuromodulated multiobjective evolutionary neurocontrollers without speciation

Abstract: Neuromodulation is a biologically-inspired technique that can adapt the per-connection learning rates of synaptic plasticity. Neuromodulation has been used to facilitate unsupervised learning by adapting neural network weights. Multiobjective evolution of neural network topology and weights has been used to design neurocontrollers for autonomous robots. This paper presents a novel multiobjective evolutionary neurocontroller with unsupervised learning for robot navigation. Multiobjective evolution of network weights and topologies (NEAT-MODS) is augmented with neuromodulated learning. NEAT-MODS is an NSGA-II based multiobjective neurocontroller that uses two conflicting objectives. The first rewards the robot when it moves in a direct manner with minimal turning; the second objective is to reach as many targets as possible. NEAT-MODS uses speciation, a selection process that aims to ensure Pareto-optimal genotypic diversity and elitism. The effectiveness of the design is demonstrated using a series of experiments with a simulated robot traversing a simple maze containing target goals. It is shown that when neuromodulated learning is combined with multiobjective evolution, better-performing neural controllers are synthesized than by evolution alone. Secondly, it is demonstrated that speciation is unnecessary in neuromodulated neuroevolution, as neuromodulation preserves topological innovation. The proposed neuromodulated approach is found to be statistically superior to NEAT-MODS alone when applied to solve a multiobjective navigation problem.

Lamarckian Inheritance in Neuromodulated Multiobjective Evolutionary Neurocontrollers

Abstract: This paper presents a novel evolutionary multiobjective neurocontroller with unsupervised learning and Lamarckian inheritance for robot navigation. Multiobjective evolution of network weights and topologies (NEAT-MODS) is augmented with Lamarckian inherited neuromodulated learning. NEAT-MODS is an NSGA-II augmented multiobjective neurocon-troller that uses two conflicting objectives. NEAT-MODS uses a selection process that aims to ensure Pareto-optimal genotypic diversity and elitism. Neuromodulation is a biologically-inspired technique that can adapt the per-connection learning rates of synaptic plasticity. Effectiveness of the design is demonstrated using a series of experiments with a simulated robot traversing a simple maze containing target goals. It is shown that when Lamarckian inheritance is combined with evolved neuromodulated learning, neural controllers are synthesized in fewer generations than by neuromodulated evolution alone. The proposed Lamarckian neuromodulated approach is found to be statistically superior to neuromodulation alone when applied to solve a multiobjective navigation problem.

Multiobjective Neuromodulated Controllers for Efficient Autonomous Vehicles with Mass and Drag in the Pursuit-Evasion Game

Abstract: Autonomous vehicles in the pursuit-evasion game, subject to the effects of mass and drag, are controlled using an evolutionary multiobjective neuromodulated controller with unsupervised learning. Multiobjective evolution of network weights and topologies (NEAT-MODS) is extended with Lamarckian-inherited neuromodulated learning. NEAT-MODS is an NSGA-II augmented multiobjective neurocontroller that uses two conflicting objectives. By evolving pursuit agents optimized with the separate and conflicting objectives of ‘capturing evaders’ and ‘minimizing energy consumption’, efficient neurocontrollers can be evolved. NEAT-MODS uses a selection process that aims to ensure Pareto-optimal genotypic diversity and elitism. Neuromodulation is a biologically-inspired technique that can adapt the per-connection learning rates of synaptic plasticity. Lamarckian inheritance allows behaviours learned during parent generations to be passed on to their offspring. The capability of the design is demonstrated in a series of experiments with a simulated evolved vehicle pursuing a basic evader vehicle. It is shown that compact and efficient neurocontrollers for pursuer agents with nonzero mass and drag, capable of capturing an optimal evader while simultaneously minimizing energy consumption, are evolved.

A growing and pruning method for a history stack neural network based adaptive controller

Abstract: This paper presents a neural network based control strategy for adaptive control of a robotic manipulator. The neural network learns the inverse dynamics of the robotic manipulator while controlling the robot on-line without any a priori knowledge of the manipulator inertial parameters or the equation of dynamics. The only assumptions that must be made about the target system are the number of inputs and outputs to the system. A history stack algorithm is used to facilitate simultaneous control and learning. Learning performance is improved by growing and pruning neurons from the neural network based on the magnitude of the trajectory error. Simulation of a two degree of freedom serial link manipulator allows verification of the effectiveness of the algorithm. Results show improved performance in comparison to a controller using the history stack alone.

Objective Comparison and Selection in Mono- and Multi-Objective Evolutionary Neurocontrollers

Abstract: Often in multi-objective problems, several elemental objectives are combined into compound objectives by using auxiliary equations to reduce these problems to just one or two objectives. Reducing the number of objectives simplifies the problem into a more easily optimized mono-objective problem, or for multi-objective problems, reduces the Pareto front to a few dimensions for easy analysis. Here, multi-objective evolutionary neurocontrollers with both compound and elemental objectives are compared to a mono-objective evolutionary neurocontroller. The goal of this research is to compare the effectiveness of individual elemental and compound objective effectiveness, and not directly compare mono- and multi-objectivity. The effectiveness of each of the objectives is determined through a series of experiments using a previously demonstrated Lamarckian-inherited neuromodulated evolutionary neurocontroller. The evolved neurocontrollers operate a simulated vehicle pursuing a basic evader vehicle in the pursuit-evasion game. Both vehicles are subject to the effects of mass and drag. It is shown that under certain circumstances, binary objectives can be unsuitable choices as objectives, and that it can be more effective to use multi-objective solutions than to combine elemental objective problems into mono-objective problems by auxiliary functions. It is also shown that the obvious choice of objective may not be the most effective choice.

Neuromodulated multiobjective evolutionary neurocontrollers without speciation

Abstract: Neuromodulation is a biologically-inspired technique that can adapt the per-connection learning rates of synaptic plasticity. Neuromodulation has been used to facilitate unsupervised learning by adapting neural network weights. Multiobjective evolution of neural network topology and weights has been used to design neurocontrollers for autonomous robots. This paper presents a novel multiobjective evolutionary neurocontroller with unsupervised learning for robot navigation. Multiobjective evolution of network weights and topologies (NEAT-MODS) is augmented with neuromodulated learning. NEAT-MODS is an NSGA-II based multiobjective neurocontroller that uses two conflicting objectives. The first rewards the robot when it moves in a direct manner with minimal turning; the second objective is to reach as many targets as possible. NEAT-MODS uses speciation, a selection process that aims to ensure Pareto-optimal genotypic diversity and elitism. The effectiveness of the design is demonstrated using a series of experiments with a simulated robot traversing a simple maze containing target goals. It is shown that when neuromodulated learning is combined with multiobjective evolution, better-performing neural controllers are synthesized than by evolution alone. Secondly, it is demonstrated that speciation is unnecessary in neuromodulated neuroevolution, as neuromodulation preserves topological innovation. The proposed neuromodulated approach is found to be statistically superior to NEAT-MODS alone when applied to solve a multiobjective navigation problem.

A Game-Learning-Based Smooth Path Planning Strategy for Intelligent Air–Ground Vehicle Considering Mode Switching

Abstract: Numerous missions in both civil and military fields involve the pursuit-evasion problem of vehicles. With vertical take-off and landing capability, the intelligent air–ground vehicle expands its feasible path to 3-D space, which has great advantages in the pursuit. This vehicle requires adequate path planning to obtain an optimal 3-D path and further improve the pursuit efficiency. The planning process of the air–ground vehicle currently faces the technical difficulties of acquiring the proper takeoff timing and position while optimizing the planning trajectory, especially in a complex environment with dense obstacles. To solve the above issues, a game-learning-based smooth path planning strategy for the intelligent air–ground vehicle considering mode switching is proposed in this article. First, a new reward function of the $Q$ -learning algorithm, considering the influence of flight obstacle crossing parameters, is presented to explore the short forward track distance. Second, in the update rule, the pursuit-evasion game acts in the mode switching decisions. During interactive learning between the vehicle and environment, this game constantly updates the Nash equilibrium solutions for mode switching and gets a series of switching decisions of the pursuer vehicle (ego vehicle). Third, a double-yaw correction for path smoothing modification is proposed to reduce turning points and avoid local path deviations. This modification provides heuristic information for the exploration of the environment, which significantly speeds up the convergence speed of the algorithm. Finally, the proposed strategy is verified on a 1000 m*1000 m map with 0–200 m obstacle height. Results show that this strategy is effective to decrease the 253-m distance compared with the traditional reinforcement learning algorithm and has a faster convergence speed. The number of trajectory direction changes is 36% less than that of the game-learning algorithm only considering mode switching. The unreasonable large angle turns are eliminated.

Lamarckian Inheritance in Neuromodulated Multiobjective Evolutionary Neurocontrollers

Abstract: This paper presents a novel evolutionary multiobjective neurocontroller with unsupervised learning and Lamarckian inheritance for robot navigation. Multiobjective evolution of network weights and topologies (NEAT-MODS) is augmented with Lamarckian inherited neuromodulated learning. NEAT-MODS is an NSGA-II augmented multiobjective neurocon-troller that uses two conflicting objectives. NEAT-MODS uses a selection process that aims to ensure Pareto-optimal genotypic diversity and elitism. Neuromodulation is a biologically-inspired technique that can adapt the per-connection learning rates of synaptic plasticity. Effectiveness of the design is demonstrated using a series of experiments with a simulated robot traversing a simple maze containing target goals. It is shown that when Lamarckian inheritance is combined with evolved neuromodulated learning, neural controllers are synthesized in fewer generations than by neuromodulated evolution alone. The proposed Lamarckian neuromodulated approach is found to be statistically superior to neuromodulation alone when applied to solve a multiobjective navigation problem.