For my bachelor and professional degree thesis, I designed a spider robot that can move through irregular terrain carrying a landmine sensor. The design included the mechanical structure, the electronics, and the control of the robot. I proposed an innovative algorithm for controlling the joints to make the robot learn to walk, using genetic algorithms and ensemble learning.
The proposed algorithm allows training an intelligent agent to maximize a reward metric without applying reinforcement learning techniques, which are usually the way to solve this type of problem.
To test the designed gait learning algorithm, I used a scaled prototype maintaining the same geometry and DOF of the robot designed for moving the landmine sensor. For my thesis, I improved the spider robot I made in 2018.
I obtained my Bachelor’s degree on September, 2019. After that, my thesis was improved and then presented to obtain my Professional Degree of Mechatronics Engineer on November, 2020.
My thesis received the following national and international awards:
- Best bachelor’s thesis and poster presentation at the PUCP Mechatronics Workshop of the semester 2019-1.
- Innovation Recognition Award at the International Mechanical Engineering Congress & Exposition (IMECE) 2019, which was celebrated in Utah, USA.
- Extraordinary Support Funding for Undergraduate Research Thesis.
- Degree thesis unanimously awarded by the tribunal with the qualification of outstanding.
Sensor calibration is vital to have valid measurements of physical activities. In this paper, we deal with adjusting the signal from a wearable force sensor against a reference scale. By using a few samples and data augmentation, we trained a neural-based regression model to correct the wearable output. For this task, we tested the novel Auto-Rotating Perceptrons (ARP). We found that a neural ARP model with sigmoid activations can outperform an identical neural network based on classic perceptrons with sigmoid and even ReLU activation.
When changing classic perceptrons to ARP, the test loss of the sigmoid networks was reduced by a factor of 15 at the cost of increasing the execution time by ∼12% (see bar graph below).
Erratum: In the oral presentation video, when I say “without learning the inference structure of the perceptron”, I mean “without altering the inference structure learned by the perceptron”.
This paper proposed an improved design of the perceptron unit to mitigate the vanishing gradient problem at deep neural networks. The results show that models with Auto-Rotating Perceptrons (ARP) can achieve better learning performance than equivalent networks with classic perceptrons.
The modification consists of adding the scalar \( \rho \) to the value that enters the activation function, as is depicted below. Geometrically, it represents a rotation of the hyperplane present in the latent space of the perceptron. The ARP is a generalization of the classic perceptrons.