Machine learning (ML) is a branch of artificial intelligence that has been developing at a dynamic pace in recent years. ML is also linked with Big Data, which are huge datasets that need special tools and approaches to process them. ML algorithms make use of data to learn how to perform specific tasks or make appropriate decisions. This paper presents a comprehensive survey of recent ML approaches that have been applied to the task of mobile robot control, and they are divided into the following: supervised learning, unsupervised learning, and reinforcement learning. The distinction of ML methods applied to wheeled mobile robots and to walking robots is also presented in the paper. The strengths and weaknesses of the compared methods are formulated, and future prospects are proposed. The results of the carried out literature review enable one to state the ML methods that have been applied to different tasks, such as the following: position estimation, environment mapping, SLAM, terrain classification, obstacle avoidance, path following, learning to walk, and multirobot coordination. The survey allowed us to associate the most commonly used ML algorithms with mobile robotic tasks. There still exist many open questions and challenges such as the following: complex ML algorithms and limited computational resources on board a mobile robot; decision making and motion control in real time; the adaptability of the algorithms to changing environments; the acquisition of large volumes of valuable data; and the assurance of safety and reliability of a robot’s operation. The development of ML algorithms for nature-inspired walking robots also seems to be a challenging research issue as there exists a very limited amount of such solutions in the recent literature.

This paper presents the application of artificial intelligence applied to image classification according to CNN (Convolutional neutral network) algorithm. Two AI (artificial intelligence) models were submitted for verification. The first was based on mobilenet algorithm, and the second was based on the application of several layers of Convolution, ReLU and Maxpooling. After examining the AI, a solution using image classification was proposed for the IRB1200 robot, which encircles symbols assigned to color saturation on the detected colors. In the introduction, articles were selected that are related to the application of AI in various industries. The second section describes mathematical relationships for algorithms used in the project for image classification. Next, a multi-task control system for a robot is described, which performs specific tasks based on image verification by CNN-based artificial intelligence. The AI model and system handling reading of the image from a camera were submitted for verification, based on the tasks to be performed by the IRB1200 robotic arm based on color recognition. Verification was carried out in the head office of a company called Sii.

This paper presents the process of retrofitting a six-point-of-freedom walking unit - a hexapod remotely controlled by Bluetooth communication based on a proprietary programme. A comparison is made to show how differences in the design of the walking unit, and in particular the number of freedom points per leg, can affect the efficiency of locomotion. In the first section, the work of other authors related to walking robots is presented. In the next section of the article, the individual components of the robot and the software are analysed and compared with the original unit to show the differences and advantages obtained by the upgrade. The last part of the article summarises the work done and shows further possibilities for the development of the project.