Browsing by Author "Goncalves, Gil"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
- Deep convolutional neural networks applied to hand keypoints estimationPublication . Santos, Bruno M.; Pais, Pedro; Ribeiro, Francisco M.; Lima, José; Goncalves, Gil; Pinto, Vítor H.Accurate estimation of hand shape and position is an important task in various applications, such as human-computer interaction, human-robot interaction, and virtual and augmented reality. In this paper, it is proposed a method to estimate the hand keypoints from single and colored images utilizing the pre-trained deep convolutional neural networks VGG-16 and VGG-19. The method is evaluated on the FreiHAND dataset, and the performance of the two neural networks is compared. The best results were achieved by the VGG-19, with average estimation errors of 7.40 pixels and 11.36 millimeters for the best cases of two-dimensional and three-dimensional hand keypoints estimation, respectively.
- Glove prototype for feature extraction applied to learning by demonstration purposesPublication . Cerqueira, Tiago; Ribeiro, Francisco; Pinto, Vítor H.; Lima, José; Goncalves, GilThis article focuses on a sensorial glove prototype capable of acquiring hand motion and estimating its pose. The presented solution features twelve inertial measurement units (IMUs) to track hand orientation. The sensors are attached to a glove to decrease the project cost. The system also focuses on sensor fusion algorithms for the IMUs and further implementations, presenting the algebraic quaternion algorithm (AQUA), used because of its modularity and intuitive implementation. An adaptation of a human hand model is proposed, explaining its advantages and its limitations. Considering that the calibration is a very important process in gyroscope performance, the online and offline calibration data was analyzed, pointing out its challenges and improvements. To better visualize the model and sensors a simulation was conducted in Unity.
- Mecanum wheel robotic platform for educational purposes: a cost-effective approachPublication . Viana, Emanuel; Pinto, Vítor H.; Lima, Jose; Goncalves, GilThis paper presents a cost-effective approach of a mecanum wheel robotic platform for educational propose on the development of an autonomous or remote controlled mobile robot with a four-wheel mecanum drive train. The main structure of the mobile robot was developed in Solidworks and it was built using additive manufacturing to validate in a real scenario. The main objective of developing this type of mobile platform was the ability to transport different types of cargo or robotic arm on industrial spaces or on rough terrain, since the implemented suspension mechanism allows the wheels contact to the floor. Another important objective is the maneuverability and the capacity to be guided in various environments, a great advantage in this type of mobile platform. An additional advantage of the developed mobile robot is the easy way to reconfigure the structure for new acquired parts.
- Modeling and realistic simulation of a dexterous robotic hand: SVH hand use-casePublication . Ribeiro, Francisco M.; Correia, Tiago; Lima, José; Goncalves, Gil; Pinto, Vítor H.Recent developments in dexterous robotic manipulation technologies allowed for the design of very compact, yet capable, multi-fingered robotic hands. These can be designed to emulate the human touch and feel, reducing the aforementioned need for human expertise in highly detailed tasks. The presented work focused on the application of two simulation platforms Gazebo and MuJoCo - to a use-case of a Schunk Five Finger Robotic Hand, coupled to the UR5 collaborative manipulator. This allowed to assess the relative appropriateness of each of these platforms.