An approach to the problem of autonomous mobile robot obstacle avoidance using Reinforcement Learning, more precisely Q-Learning, is presented in this paper. Reinforcement Learning in Robotics has been a challenging topic for the past few years. The ability to equip a robot with a powerful enough tool to allow an autonomous discovery of an optimal behavior through trial-and-error interactions with its environment has been a reason for numerous deep research projects. In this paper, two different Q-Learning approaches are presented as well as an extensive hyperparameter study. These algorithms were developed for a simplistically simulated Bot'n Roll ONE A (Fig. 1). The simulated robot communicates with the control script via ROS. The robot must surpass three levels of iterative complexity mazes similar to the ones presented on RoboParty [1] educational event challenge. For both algorithms, an extensive hyperparameter search was taken into account by testing hundreds of simulations with different parameters. Both Q-Learning solutions develop different strategies trying to solve the three labyrinths, enhancing its learning ability as well as discovering different approaches to certain situations, and finishing the task in complex environments.

A 1D MEMS (Micro-Electro-Mechanical Systems) mirror for LiDAR applications, based on vertically asymmetric comb-drive electrostatic actuators, is presented in this work employing a novel fabrication process. This novel micromachining process combines typical SOI-based bulk micromachining and grayscale lithography, enabling the fabrication of combs actuators with asymmetric heights using a single lithography step in the active layer. With this technique, the fabrication process is simplified, and the overall costs are reduced since the number of required lithography steps decrease. The fabricated mirrors present self-aligned electrodes with a 2.8 μm gap and asymmetric heights of the movable and the fixed electrodes of 20 μm and 50 μm, respectively. These asymmetric actuators are an essential feature for the operation mode of this device, enabling both in resonant and static mode operation. A mirror field of view (FOV) of 54° at 838 Hz was achieved under low-pressure, when resonantly operated, and a FOV of 0.8° in the static mode.

This paper describes the design and development of an autonomous robot for the Robot@Factory league at “Festival Nacional de Robótica 2016”, held in Bragança, Portugal. This paper describes all the hardware and software components developed for a localization and performance of the robot according to the rules. The challenge consists of a table setup that recreates an industrial environment where a robot has to successfully transport boxes from an initial warehouse to the final warehouse. The destination to which the robot has to carry each box, depends on the state of the box, i.e., depending on the box LED color, even though in some cases the robot has to leave the box temporarily in the called processing machines (which are intermediate stations). The most significant innovation feature of this robot prototype consists of the possibility of carrying up to three boxes simultaneously while being able to select which box to drop. This project was developed with great success, since the team managed to reach the 3rd place in the competition.

A very high-resolution SOI (silicon-on-insulator) MEMS (Micro-Electro-Mechanical Systems) accelerometer for geodetic space grade applications using pull-in time measurements is presented here. Parallelplates implemented in the handle-layer are used to provide the necessary squeeze-film damping, while increasing the effective-mass. Large mass (126 mg) devices with low-Q (quality factor of 0.53) have been fabricated and tested using time transduction. The high measured sensitivity of 1.9 ns/ng enables the use of the device in ultra-high resolution and low-dynamic range applications.

Environmental factors, such as pressure and temperature, are known to contribute to the formation of ulcers that seriously affect bedridden individuals. Researchers have proposed several technologies to achieve the long-term monitoring of those parameters, usually relying on sensing mats, which poses difficulties in correlating the measurements with specific parts of the body. In this work, we aim to develop microsensors to be integrated into patient clothing. They should be highly flexible, thin with a small footprint, and can be achieved by taking advantage of the microfabrication on polyimide (PI) thin-film substrates (total device thicknesses below 30 µm). Both resistive and capacitance transduction mechanisms were explored, targeting operation ranges of 1 to 40 kPa and 24 to 42 °C. The sensors were integrated into textiles using silicone elastomers and electrical connections based on conductive silver yarn. The experimental characterization showed a nominal capacitance of 21 pF, a sensitivity of −8.44 fF/kPa for the pressure sensors, and a 0.0021 Ω/Ω°C sensitivity of the temperature sensor (with resistance of 29 kΩ at 22 °C). The proposed approach can potentially be implemented not only in wearable devices but also in many other applications for health monitoring or human–machine interfaces.

This paper describes the design and development of an autonomous robotic manipulator with four degrees of freedom. The manipulator is named RACHIE - “Robotic Arm for Collaboration with Humans in Industrial Environment”. The idea was to create a smaller version of the industrial manipulators available on the market. The mechanical and electronic components are presented as well as the software algorithms implemented on the robot. The manipulator has as its primary goal the detection and organization of cans by color and defects. The robot can detect a human operator so it can deliver defective cans by collaborating with him/her on an industrial environment. To be able to perform such task, the robot has implemented a machine learning algorithm, a Haar feature-based cascade classifier, on its vision system to detect cans and humans. On the handler motion, direct and inverse kinematics were calculated and implemented, and its equations are described in this paper. This robot presents high reliability and robustness in the task assigned. It is low-cost as it is a small version of commercial ones, making it optimized for smaller tasks.