Hexapod Robot Gait Switching for Energy Consumption and Cost of Transport Management Using Heuristic Algorithms

Shaping the energy curves of a servomotor-based hexapod robot

The advantageous versatility of hexapod robots is often accompanied by high power consumption, while animals have evolved an energy efficient locomotion. However, there are a lack of methods able to compare and apply animals' energetic optimizations to robots. In this study, we applied our method to a full servomotor-based hexapod robot to evaluate its energetic performance. Using an existing framework based on the laws of thermodynamics, we estimated four metrics using a dedicated test bench and a simulated robotic leg. We analyzed the characteristics of a single leg to shape the energetic profile of the full robot to a given task. Energy saving is improved by 10% through continuous duty factor adjustment with a 192% increase in power maximization. Moreover, adjusting the robot's velocity by the step length and associating this with gait switching, reduces the power loss by a further 10% at low-speed locomotion. However, unlike in animals, only one unique optimal operating point has been revealed, which is a disadvantage caused by the low energetic efficiency of servomotor-based hexapods. Thus, these legged robots are severely limited in their capacity to optimally adjust their locomotion to various tasks-a counter-intuitive conclusion for a supposedly versatile robot.

Interoperability between Real and Virtual Environments Connected by a GAN for the Path-Planning Problem

Path planning is a fundamental issue in robotic systems because it requires coordination between the environment and an agent. The path-planning generator is composed of two modules: perception and planning. The first module scans the environment to determine the location, detect obstacles, estimate objects in motion, and build the planner module’s restrictions. On the other hand, the second module controls the flight of the system. This process is computationally expensive and requires adequate performance to avoid accidents. For this reason, we propose a novel solution to improve conventional robotic systems’ functions, such as systems having a small-capacity battery, a restricted size, and a limited number of sensors, using fewer elements. A navigation dataset was generated through a virtual simulator and a generative adversarial network to connect the virtual and real environments under an end-to-end approach. Furthermore, three path generators were analyzed using deep-learning solutions: a deep convolutional neural network, hierarchical clustering, and an auto-encoder. Since the path generators share a characteristic vector, transfer learning approaches complex problems by using solutions with fewer features, minimizing the costs and optimizing the resources of conventional system architectures, thus improving the limitations with respect to the implementation in embedded devices. Finally, a visualizer applying augmented reality was used to display the path generated by the proposed system.

Modelling and Control of Mechatronic and Robotic Systems

Nowadays, the modelling and control of mechatronic and robotic systems is an open and challenging field of investigation in both industry and academia [...]