Collaborating Authors


Talking Robotics' seminars of January – April 2021 (with videos and even a musical summary!)


Talking Robotics is a series of virtual seminars about Robotics and its interaction with other relevant fields, such as Artificial Intelligence, Machine Learning, Design Research, Human-Robot Interaction, among others. They aim to promote reflections, dialogues, and a place to network. In this seminars compilation, we bring you 7 talks (and a half?) from current roboticists for your enjoyment. Filipa Correia received a M.Sc. in Computer Science from University of Lisbon, Portugal, 2015. She is currently a junior researcher at GAIPSLab and she is pursuing a Ph.D. on Human-Robot Interaction at University of Lisbon, Portugal.

Council Post: Using AI And Machine Learning To Break Past The Constraints Of The 'New Normal'


Rohana Meade is the President and CEO at Synergy Technical, a leading-edge technology services and solutions company. As we kick off 2021, business technology leaders around the globe are kicking off their 2021 IT strategic plans. If 2020 taught us anything in the technology world, it was that if you weren't refining your business processes using advances in technology, you should be. Rather than just thinking outside the box, technology leaders should be assuming that there is no box at all. In 2021, artificial intelligence and machine learning technologies will continue to become more mainstream.

How To Measure ML Model Accuracy


Machine learning (ML) is about making predictions about new data based on old data. The quality of any machine-learning algorithm is ultimately determined by the quality of those predictions. However, there is no one universal way to measure that quality across all ML applications, and that has broad implications for the value and usefulness of machine learning. "Every industry, every domain, every application has different care-abouts," said Nick Ni, director of product marketing, AI and software at Xilinx. "And you have to measure that care-about." Classification is the most familiar application, and "accuracy" is the measure used for it. But even so, there remain disagreements about exactly how accuracy should be measured or what it should mean. With other applications, it's much less clear how to measure the quality of results.

AI And EdTech: A Match Made In Heaven?


COVID 19 has changed every aspect of our lives, and in no smaller manner, the lives of our children. It has also placed a renewed focus on how education is delivered, with schools having gone entirely online and parents at home with their kids. There is a broad sense that while some aspects of education will return to pre-pandemic patterns (with schools planning reopenings with vaccinated teachers), the classroom of the future will be fundamentally altered. The past year has taught kids, parents, and teachers what is possible by adding technology. Once no longer forced to be online, we will be free to combine the best of what we knew and what we have newly learned to create a better learning world for all.

AI Sudoku Solver


Sudoku is a puzzle in which players insert the numbers one to nine into a grid consisting of nine squares subdivided into a further nine smaller squares in such a way that every number appears once in each horizontal line, vertical line, and square. Using OpenCV, Deep Learning, and Backtracking Algorithm, We can solve the sudoku puzzle. First, build the Character Recognition model that can extract digits from a Sudoku grid image and then work on a backtracking approach to solve it. The model Convolution Neural Network(CNN) uses Keras (keras 2.3.1) on Tensorflow for Digit Recognition. Looking for a sudoku puzzle in the image: In this part, we'll be focusing on how to extract the sudoku grid i.e. our Region of Interest (ROI) from the input image.

AI's Greatest Challenges


Artificial Intelligence may be one of the most impressive human achievements and offers endless opportunities for companies willing to foster this technology. As the benefits of main AI elements such as Machine Learning, Data Analysis, and Predictive Analysis are undeniable, here are a few of the biggest challenges that companies may face while introducing AI to their day-to-day operations. In the AI project's initial stages, the key project stakeholders need to inform the business that the technology is not perfect and that its introduction might create some temporary inconveniences. Once the AI application gets deployed, it needs to be used and trusted to be continually improved. Unfortunately, learning and developing new skills and breaking up with old habits don't come easily for some employees.

Adding AI to Autonomous Weapons Increases Risks to Civilians in Armed Conflict


Earlier this month, a high-level, congressionally mandated commission released its long-awaited recommendations for how the United States should approach artificial intelligence (AI) for national security. The recommendations were part of a nearly 800-page report from the National Security Commission on AI (NSCAI) that advocated for the use of AI but also highlighted important conclusions on key risks posed by AI-enabled and autonomous weapons, particularly the dangers of unintended escalation of conflict. The commission identified these risks as stemming from several factors, including system failures, unknown interactions between these systems in armed conflict, challenges in human-machine interaction, as well as an increasing speed of warfare that reduces the time and space for de-escalation. These same factors also contribute to the inherent unpredictability in autonomous weapons, whether AI-enabled or not. From a humanitarian and legal perspective, the NSCAI could have explored in more depth the risks such unpredictability poses to civilians in conflict zones and to international law.

Inductive Mutual Information Estimation: A Convex Maximum-Entropy Copula Approach Machine Learning

We propose a novel estimator of the mutual information between two ordinal vectors $x$ and $y$. Our approach is inductive (as opposed to deductive) in that it depends on the data generating distribution solely through some nonparametric properties revealing associations in the data, and does not require having enough data to fully characterize the true joint distributions $P_{x, y}$. Specifically, our approach consists of (i) noting that $I\left(y; x\right) = I\left(u_y; u_x\right)$ where $u_y$ and $u_x$ are the copula-uniform dual representations of $y$ and $x$ (i.e. their images under the probability integral transform), and (ii) estimating the copula entropies $h\left(u_y\right)$, $h\left(u_x\right)$ and $h\left(u_y, u_x\right)$ by solving a maximum-entropy problem over the space of copula densities under a constraint of the type $\alpha_m = E\left[\phi_m(u_y, u_x)\right]$. We prove that, so long as the constraint is feasible, this problem admits a unique solution, it is in the exponential family, and it can be learned by solving a convex optimization problem. The resulting estimator, which we denote MIND, is marginal-invariant, always non-negative, unbounded for any sample size $n$, consistent, has MSE rate $O(1/n)$, and is more data-efficient than competing approaches. Beyond mutual information estimation, we illustrate that our approach may be used to mitigate mode collapse in GANs by maximizing the entropy of the copula of fake samples, a model we refer to as Copula Entropy Regularized GAN (CER-GAN).

Behavior coordination for self-adaptive robots using constraint-based configuration Artificial Intelligence

Autonomous robots may be able to adapt their behavior in response to changes in the environment. This is useful, for example, to efficiently handle limited resources or to respond appropriately to unexpected events such as faults. The architecture of a self-adaptive robot is complex because it should include automatic mechanisms to dynamically configure the elements that control robot behaviors. To facilitate the construction of this type of architectures, it is useful to have general solutions in the form of software tools that may be applicable to different robotic systems. This paper presents an original algorithm to dynamically configure the control architecture, which is applicable to the development of self-adaptive autonomous robots. This algorithm uses a constraint-based configuration approach to decide which basic robot behaviors should be activated in response to both reactive and deliberative events. The algorithm uses specific search heuristics and initialization procedures to achieve the performance required by robotic systems. The solution has been implemented as a software development tool called Behavior Coordinator CBC (Constraint-Based Configuration), which is based on ROS and open source, available to the general public. This tool has been successfully used for building multiple applications of autonomous aerial robots.

Multi-Label Classification Neural Networks with Hard Logical Constraints Artificial Intelligence

Multi-label classification (MC) is a standard machine learning problem in which a data point can be associated with a set of classes. A more challenging scenario is given by hierarchical multi-label classification (HMC) problems, in which every prediction must satisfy a given set of hard constraints expressing subclass relationships between classes. In this paper, we propose C-HMCNN(h), a novel approach for solving HMC problems, which, given a network h for the underlying MC problem, exploits the hierarchy information in order to produce predictions coherent with the constraints and to improve performance. Furthermore, we extend the logic used to express HMC constraints in order to be able to specify more complex relations among the classes and propose a new model CCN(h), which extends C-HMCNN(h) and is again able to satisfy and exploit the constraints to improve performance. We conduct an extensive experimental analysis showing the superior performance of both C-HMCNN(h) and CCN(h) when compared to state-of-the-art models in both the HMC and the general MC setting with hard logical constraints.