Liguo Weng

Neural-Memory Based Control of Micro Air Vehicles (MAVs) with Flapping Wings

This paper addresses the problem of wing motion control of flapping wing Micro Air Vehicles (MAVs). Inspired by hummingbirds wing structure as well as the construction of its skeletal and muscular components, a dynamic model for flapping wing is developed. As the model is highly nonlinear and coupled with unmeasurable disturbances and uncertainties, traditional strategies are not applicable for flapping wing motion control. A new approach called neural-memory based control is proposed in this work. It is shown that this method is able to learn from past control experience and current/past system behavior to improve its performance during system operation. Furthermore, much less information about the system dynamics is needed in construction such a control scheme as compared with traditional NN based methods. Both theoretical analysis and computer simulation verify its effectiveness.

Bio-Inspired Control Approach to Multiple Spacecraft Formation Flying

This work addresses the problem of formation control for multiple spacecraft in a Planetary Orbital Environment (POE). Due to the diverse interferences and uncertainties in outer space, traditional control methods encounter great difficulties in this area. A new control approach inspired by human memory system is proposed, which is shown to be capable of learning from past control experience and current behavior to improve its performance and demands much less system dynamic information as compared with traditional controls. Both theoretical analysis and computer simulation verify its effectiveness.

Path planning and path tracking control of unmanned ground vehicles (UGVs)

Unmanned ground vehicles (UGVs) will be playing increasingly important role in the future battlefields. How to automatically guide and control UGVs under varying environment conditions represents a challenging issue. This paper presents a novel approach to achieving path planning and path tracking of UGVs under dynamic environments. We apply the topology theory to find the optimal path given any starting and ending points. Algorithms are developed to construct discrete points representing all the possible trajectories, from which an optimal path is identified for the UGV to track. The control scheme used is based on memory based control theory. The optima] path can be dynamically changed according to information gathered from the surrounding environment by the sensor and also the UGV can dynamically track the path using the developed tracking control algorithms. Both theoretic and simulation studies will show the effectiveness of the method.

Close Formation Flight Control of Multi-UAVs via Fuzzy Logic Technique

This chapter explored a new method to achieve close formation tracking control of multi-UAVs by applying fuzzy logic theory. The formation trajectory is achieved by the control of Wingman’s heading velocity and heading angle while the lead UAV is maneuvering the given mission path.

Neuro-adaptive control method for antilock braking systems

The braking effectiveness of antilock braking system (ABS) could be degraded for rough road conditions (e.g., icy/snowy roads). In this work, a neuro-adaptive control design method is proposed for improving the performance of ABS. A neuro-adaptive unit is constructed to compensate external disturbances and uncertain dynamics due to road condition variation. This method does not involve analytical estimation of the upper bound on the reconstruction error and lumped uncertainties of the system, simplifying the design process and online computation. The performance of the developed control scheme is verified via simulation.

Immunology-inspired swarm coordination with application to multiple combat UGV systems

Immune system has several interesting and desirable properties such as adaptability, robustness, flexibility, archival memory, and distributed cognition abilities. This paper presents a multi-agent scheme with swarm coordination functions inspired by immune system. It is shown that by using local communication, each agent is able to select its favorite strategy based on distributed sensing, which leads to successful swarm behavior, and performs well even under dynamically changing environment. Furthermore, in the proposed scheme a thymus-like global coordination mechanism called a critic here is introduced to prevent undesirable crowding, thus improving the overall swarming behavior as verified by numerical simulation on a collection of unmanned ground vehicles (UGVs).

Human Memory/Learning Inspired Approach for Attitude Control of Crew Exploration Vehicles (CEVs)

This paper addresses the problem of attitude control of crew exploration vehicle (CEV). Unlike traditional spacecraft with surface deflections for attitude control, CEV uses RCS jet engines for attitude adjustment, which calls for control algorithms for firing the small propulsion engines mounted in the vehicle. In this work, by combining both actuation and attitude dynamics, we develop a strategy to control the vehicle attitude via adjusting reaction control system (RCS) throttle angles. Since the resultant (combined) dynamics of the vehicle are highly nonlinear and coupled with significant uncertainties, we explore a control approach based on human memory and learning mechanism, which does not reply on precise system information dynamics. Furthermore, the overall control scheme has simple structure and demands much less computation as compared with most existing methods, making it attractive for real-time implementation. The effectiveness of this approach is also verified via simulation.

Immune system inspired fault detection and identification with application to crew exploration vehicles

Immune system exhibits robust, adaptive and highly distributed cognitive capabilities comparable to the brain. It learns during its lifetime to differentiate and eliminate non-self from self substances of the body by some interesting mechanisms, such as mutation and cloning. In this work, we explore a new approach to fault detection and identification by mimicking the mechanisms of immune system. The developed fault detection and identification system (FDIS) is able to detect and identify diverse system faults dynamically. Moreover, as a learning system, the proposed FDIS can automatically adjust its detecting accuracy and is adaptive to new type of faults during its operation. Simulation on fault-detection in crew exploration vehicle (CEV) is conducted and the results verify the effectiveness of the proposed method

Pitch-Depth Control of Submarine Operating in Shallow Water via Neuro-adaptive Approach

This chapter presented a neuro-adaptive control for depth and pitch control of submarine operating in shallow waters. The control scheme is based on two neural-network (NN) units which are shown to be effective in attenuating the reconstruction error and other lumped system uncertainties. Stable on-line weight-tuning algorithms are derived based on Lyapunov’s stability theory. Variable heading speed and changing center of gravity are taken into consideration in control design. Theoretical analyses and simulations prove the efficacy of the proposed control scheme in dealing with external disturbances as well as system nonlinearities, uncertainties, and parameter variations.

Neuro Robust Adaptive Descending Control of Space Vehicles

Accurate descending control is crucial to ensure safe operation of space exploration vehicles. This work investigates automatic trajectory tracking control of space vehicles during landing phase. A set of algorithms for adjusting vehicle heading angle, heading speed and altitude are derived using adaptive robust and neural network control techniques. It is shown that with the proposed control algorithms, external disturbances and coupled dynamics inherent in the system are effectively compensated. Simulations on various flight conditions also confirm the effectiveness of the proposed methods.