OptiDepthNet : A Real-time Unsupervised Monocular Depth Estimation Network

With the development of depth learning, the accuracy and effect of the algorithm applied to monocular depth estimation have been greatly improved, but the existing algorithms need a lot of computing resources. At present, how to apply the existing algorithms to UAV and its small robot is an urgent need.Based on full convolution neural network and Kitti dataset, this paper uses deep separable convolution to optimize the network architecture, reduce training parameters and improve computing speed. Experimental results show that our method is very effective and has a certain reference value in the development direction of monocular depth estimation algorithm.

A Mobile Robot with Omnidirectional Tracks—Design and Experimental Research

This article deals with the design and testing of mobile robots equipped with drive systems based on omnidirectional tracks. These are new mobile systems that combine the advantages of a typical track drive with the advantages of systems equipped with omnidirectional Mecanum wheels. The omnidirectional tracks allow the robot to move in any direction without having to change the orientation of its body. The mobile robot market (automated construction machinery, mobile handle robots, mobile platforms, etc.) constantly calls for improvements in the manoeuvrability of vehicles. Omnidirectional drive technology can meet such requirements. The main aim of the work is to create a mobile robot that is capable of omnidirectional movement over different terrains, and also to conduct an experimental study of the robot’s operation. The paper presents the construction and principles of operation of a small robot equipped with omnidirectional tracks. The robot’s construction and control system, and also a prototype made with FDM technology, are described. The trajectory parameters of the robot’s operation along the main and transverse axes were measured on a test stand equipped with a vision-based measurement system. The results of the experimental research became the basis for the development and experimental verification of a static method of correcting deviations in movement trajectory.

Study of Mosquito Aerodynamics for Imitation as a Small Robot and Flight in a Low-Density Environment

In terms of their flight and unusual aerodynamic characteristics, mosquitoes have become a new insect of interest. Despite transmitting the most significant infectious diseases globally, mosquitoes are still among the great flyers. Depending on their size, they typically beat at a high flapping frequency in the range of 600 to 800 Hz. Flapping also lets them conceal their presence, flirt, and help them remain aloft. Their long, slender wings navigate between the most anterior and posterior wing positions through a stroke amplitude about 40 to 45°, way different from their natural counterparts (>120°). Most insects use leading-edge vortex for lift, but mosquitoes have additional aerodynamic characteristics: rotational drag, wake capture reinforcement of the trailing-edge vortex, and added mass effect. A comprehensive look at the use of these three mechanisms needs to be undertaken—the pros and cons of high-frequency, low-stroke angles, operating far beyond the normal kinematic boundary compared to other insects, and the impact on the design improvements of miniature drones and for flight in low-density atmospheres such as Mars. This paper systematically reviews these unique unsteady aerodynamic characteristics of mosquito flight, responding to the potential questions from some of these discoveries as per the existing literature. This paper also reviews state-of-the-art insect-inspired robots that are close in design to mosquitoes. The findings suggest that mosquito-based small robots can be an excellent choice for flight in a low-density environment such as Mars.

SMA micro-hand implemented in small robot for generating gestures

Research on robots that can be used for communication with humans has become popular in recent years. Communication robots should ideally be as small as an infant in order to reduce the user’s feeling of threat. In addition, non-verbal communication (such as gestures) is also important in facilitating smooth interactions between humans and robots. There are currently a few communication robots that are small sized and can generate hand gestures. In this paper, we propose a small robot hand, which is optimized for gesture communication by using a shape memory alloy (SMA). The SMA employed is a Ti–Ni alloy, which is used as an actuator. The SMA shrinks when it transforms into the austenite phase at temperatures higher than the transformation temperature. When it is in the martensitic phase at a lower temperature, it is expanded by an external force. Each finger of the robot hand is driven by an individual SMA wire. The specifications of the small robot including the hand size, operation angles in each finger joint, response times and power consumption were determined according to the human finger and existing small communication robots. These required specifications have been fulfilled by carefully designing the geometry and heating/cooling power control. A questionnaire-based survey was also conducted with a robot hand. The five-finger hand was successfully shown to generate recognizable symbolic gestures.

Influence of Social Distance Expressed by Driving Support Agent’s Utterance on Psychological Acceptability

In this study, we discuss the psychological acceptability of an utterance strategy used by the Driving Support Agent (DSA). Previous literature regarding DSA suggests that the adoption of a small robot as a form will increase acceptability. However, the agent’s utterance has been reported as a problem faced by the user. Therefore, in this study, we designed the agent’s utterance using politeness strategy as described by Brown and Levinson’s famous sociolinguistics and pragmatics theory and analyzed its acceptability through a participant-based experiment. In this experiment, we used positive and negative politeness strategies (PPS and NPS, respectively). In general, PPS is utilized to reflect the desire to be liked/recognized by others, whereas NPS is utilized to reflect the need for not wanting to be disturbed by others. Based on our results, PPS was rated high compared to NPS (n = 197). Therefore, many participants highly evaluated PPS. However, there was a group of participants who appreciated NPS. There were also participants who evaluated the two strategies equally. The number of participants in these three groups was observed at 4:1:1. This result contributes as an index on the utterance design of the DSA.

Swarm Robots in Mechanized Agricultural Operations: Roadmap for Research

Agricultural mechanization is an area of knowledge that has evolved a lot over the past century, its main actors being agricultural tractors that, in 100 years, have increased their powers by 3,300%. This evolution has resulted in an exponential increase in the field capacity of such machines. However, it has also generated negative results such as excessive consumption of fossil fuel, excessive weight on the soil, very high operating costs, and millionaire acquisition value. This paper aims to present an antiparadigmatic alternative in this area. It is proposing a swarm of small electric robotic tractors that together have the same field capacity as a large tractor with an internal combustion engine. A comparison of costs and field capacity between a 270 kW tractor and a swarm of ten swarm tractors of 24 kW each was carried out. The result demonstrated a wide advantage for the small robot team. It was also proposed the preliminary design of an electric swarm robot tractor. Finally, research challenges were suggested to operationalize such a proposal, calling on the Brazilian Robotics Research Community to elaborate a roadmap for research in the area of swarm robot for mechanized agricultural operations.