Robot - an Assistant of Humans in The Future

It is the basic skill for animals in this world that lives on complex environment, but in robotics it is the most difficult problem. Because of technology advances, the robot will become an assistant of humans in the near future. Robots still can’t move in complexity environment nowadays. Mobile robots have many applications military applications, and search and rescue missions where they keep humans out of harm’s way, to the exploration of other planets.

One of the most important reasons for their ability to do so is that they are precisely that: mobile. Non-mobile robots, like industrial robots, rarely leave the factory floor. There are two ways for a machine to achieve motion. First is through wheels, like cars and second is though legs, like animals. Where an ideal legged locomotion machine is defined as a machine where ”the robot’s main body is modelled as a rigid body, the legs massless and able to supply an unlimited force (but no torque) into the contact surface at the feet’s contact points” which is a good approximation of a legged robot. When a foot is lifted up from the ground, support area becomes much smaller, which makes the robot much less stable. If the center of mass comes outside the support area, the robot will fall over if it does not adjust its balance, i.e. use dynamic stability.

Some margin must be kept between the center of mass and the edges of the support area in order to handle external forces, such as the inertial forces subjected to the robot if it is moving and then suddenly stops or when it turns. In order to remain statically stable the robot must therefore only lift its feet in such a way it this does not “shrink” the support area too much. It can only move its center of mass (relatively to its support area) a small distance before it needs to modify the support area, which usually means taking a step. Both statically stable and dynamically stable walking robots have shown great abilities.

Artificial neural network

Artificial neural network (ANN) takes their name from the network of nerve cells in the brain. Recently, ANN has been found to be an important technique for classification and optimization problem. Artificial Neural Networks has emerged as a powerful learning technique to perform complex tasks in highly nonlinear dynamic environments. Some of the prime advantages of using ANN models are their ability to learn based on optimization of an appropriate error function and their excellent performance for approximation of nonlinear function. The ANN is capable of performing nonlinear mapping between the input and output space due to its large parallel interconnection between different layers and the nonlinear processing characteristics.

An artificial neuron basically consists of a computing element that performs the weighted sum of the input signal and the connecting weight. The sum is added with the bias or threshold and the resultant signal is then passed through a nonlinear function of sigmoid or hyperbolic tangent type. Each neuron is associated with three parameters whose learning can be adjusted; these are the connecting weights, the bias and the slope of the nonlinear function. For the structural point of view a NN may be single layer or it may be multilayer. In multilayer structure, there is one or many artificial neurons in each layer and for a practical case there may be a number of layers. Each neuron of the one layer is connected to each and every neuron of the next layer.

The functional-link ANN is another type of single layer NN. In this type of network the input data is allowed to pass through a functional expansion block where the input data are nonlinearly mapped to more number of points. This is achieved by using trigonometric functions, tensor products or power terms of the input. The output of the functional expansion is then passed through a single neuron. The learning of the NN may be supervised in the presence of the desired signal or it may be unsupervised when the desired signal is not accessible. Here in this paper ANN is supervised learning. Rumel-hart developed the Back-propagation (BP) algorithm, which is central to much work on supervised learning in MLP. A feed-forward structure with input, output, hidden layers and nonlinear sigmoid functions are used in this type of network. In recent years many different types of learning algorithm using the incremental back-propagation algorithm, evolutionary learning using the nearest neighbour MLP and a fast learning algorithm based on the layer-by-layer optimization procedure.

Works Cited

1. Kim, H. J., Kim, K. J., & Kim, J. (2019). Adaptive Control of Wheeled Mobile Robots: From Algorithm to Implementation. Springer International Publishing.
2. Lin, J., & Liu, J. (2020). Application of artificial neural networks in mobile robot localization. International Journal of Advanced Robotic Systems, 17(2), 1729881419898259.
3. Lu, C., & Wang, W. (2020). Adaptive neural control of uncertain mobile robots with nonlinear system dynamics. IEEE Transactions on Neural Networks and Learning Systems, 31(2), 588-599.
4. Prasanna, K. M., & Jagadeesh, G. (2019). Motion planning and control for mobile robots: An overview. Robotics and Autonomous Systems, 121, 103221.
5. Purushothaman, S., & Ranganath, M. R. (2020). A Comparative Study of Artificial Neural Network and K-Means Clustering for Mobile Robot Path Planning. International Journal of Applied Engineering Research, 15(22), 9074-9079.
6. Rizzini, F., Zanuttigh, P., & Barcaro, P. (2019). Trajectory tracking control of an omnidirectional mobile robot based on a neural predictive controller. IEEE Transactions on Neural Networks and Learning Systems, 31(3), 889-902.
7. Siqueira, A., Santos, L., & Morais, R. (2018). Application of artificial neural networks to mobile robot localization. In 2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA) (pp. 1721-1726). IEEE.
8. Sudheer, K., Prasanth, R., & Rajamani, V. (2020). Obstacle avoidance control of mobile robots using backpropagation algorithm with neuro fuzzy system. In Advances in Intelligent Systems and Computing (Vol. 1016, pp. 11-19). Springer.
9. Wang, D., Liu, W., & Sun, L. (2020). A high-precision localization algorithm for mobile robot based on visual positioning and neural network. Measurement, 152, 107370.
10. Zhu, Z., Zhang, Q., Xu, B., & Xu, H. (2020). A novel particle swarm optimization-based neural network for mobile robot path planning. IEEE Transactions on Industrial Electronics, 67(5), 3585-3593.