Path planning creates the shortest path from the source to the destination based on sensory information obtained from the environment. Within path planning, obstacle avoidance is a crucial task in robotics, as the autonomous operation of robots needs to reach their destination without collisions. Obstacle avoidance algorithms play a key role in robotics and autonomous vehicles. These algorithms enable robots to navigate their environment efficiently, minimizing the risk of collisions and safely avoiding obstacles. This article provides an overview of key obstacle avoidance algorithms, including classic techniques such as the Bug algorithm and Dijkstra’s algorithm, and newer developments like genetic algorithms and approaches based on neural networks. It analyzes in detail the advantages, limitations, and application areas of these algorithms and highlights current research directions in obstacle avoidance robotics. This article aims to provide comprehensive insight into the current state and prospects of obstacle avoidance algorithms in robotics applications. It also mentions the use of predictive methods and deep learning strategies.

This paper suggests low-cost fuzzy control solutions that ensure the improvement of control system (CS) performance indices by merging the benefits of fuzzy control and iterative learning control (ILC). The solutions are expressed in terms of three fuzzy CS (FCS) structures that employ ILC algorithms and a unified design method focused on Takagi-Sugeno proportional-integral fuzzy controllers (PI-FCs). The PI-FCs are dedicated to a class of servo systems with linear/linearized controlled plants characterized by second-order dynamics and integral type. The invariant set theorem by Krasovskii and LaSalle with quadratic Lyapunov function candidates is applied to guarantee the convergence of the ILC algorithms and enable proper setting of the PI-FC parameters. The linear PI controller parameters tuned by the extended symmetrical optimum method are mapped onto the PI-FC ones by the modal equivalence principle. Real-time experimental results for a dc-based servo speed CS are included.

The main objective of this paper is to study the recently proposed tensor-product-distributed-compensation (TPDC)-based control design framework in the case of tracking control design of a benchmark problem. The TPDC is a combination of the tensor product model transformation and the parallel distributed compensation framework. In this paper, we investigate the effectiveness of the TPDC design. We study how it can be uniformly and readily executed without analytical derivations. We show that the TPDC is straightforward and numerically tractable, and is capable of guaranteeing various different control performances via linear matrix inequality (LMI) conditions. All these features are studied via the state feedback trajectory control design of the translational oscillations with an eccentric rotational proof mass actuator system. The trajectory tracking capability for various tracking commands is optimized here by decay rate LMI conditions. Constraints on the output and control of the closed-loop system are also considered by LMI conditions. We present numerical simulations of the resulting closed-loop system to validate the control design

Here we aim to lay the theoretical foundations of human-robot relationship drawing upon insights from disciplines that govern relevant human behaviors: ecology and ethology. We show how the paradox of the so called “uncanny valley hypothesis” can be solved by applying the “niche” concept to social robots, and relying on the natural behavior of humans. Instead of striving to build human-like social robots, engineers should construct robots that are able to maximize their performance in their niche (being optimal for some specific functions), and if they are endowed with appropriate form of social competence then humans will eventually interact with them independent of their embodiment. This new discipline, which we call ethorobotics, could change social robotics, giving a boost to new technical approaches and applications.

A recently developed technique of mod- elling parameter varying dynamical systems is the Ten- sor Product model representation, where a system is de- composed to convex combination of several parameter- invariant models. Effectiveness and tractability of the representation depends strongly on the type of the ap- plied convex combination. This paper presents an algo- rithm, which generates a special type of convex combi- nation, the RNO-INO representation. An example is also introduced.