Search

Abstract Taste perception plays a pivotal role in guiding nutrient intake and aiding in the avoidance of potentially harmful substances through five basic tastes - sweet, bitter, umami, salty, and sour. Taste perception originates from molecular interactions in the oral cavity between taste receptors and chemical tastants. Hence, the recognition of taste receptors and the subsequent perception of taste heavily rely on the physicochemical properties of food ingredients. In recent years, several advances have been made towards the development of machine learning-based algorithms to classify chemical compounds’ tastes using their molecular structures. Despite the great efforts, there remains significant room for improvement in developing multi-class models to predict the entire spectrum of basic tastes. Here, we present a multi-class predictor aimed at distinguishing bitter, sweet, and umami, from other taste sensations. The development of a multi-class taste predictor paves the way for a comprehensive understanding of the chemical attributes associated with each fundamental taste. It also opens the potential for integration into the evolving realm of multi-sensory perception, which encompasses visual, tactile, and olfactory sensations to holistically characterize flavour perception. This concept holds promise for introducing innovative methodologies in the rational design of foods, including pre-determining specific tastes and engineering complementary diets to augment traditional pharmacological treatments.

Abstract The umami taste is one of the five basic taste modalities normally linked to the protein content in food. The implementation of fast and cost-effective tools for the prediction of the umami taste of a molecule remains extremely interesting to understand the molecular basis of this taste and to effectively rationalise the production and consumption of specific foods and ingredients. However, the only examples of umami predictors available in the literature rely on the amino acid sequence of the analysed peptides, limiting the applicability of the models. In the present study, we developed a novel ML-based algorithm, named VirtuousUmami, able to predict the umami taste of a query compound starting from its SMILES representation, thus opening up the possibility of potentially using such a model on any database through a standard and more general molecular description. Herein, we have tested our model on five databases related to foods or natural compounds. The proposed tool will pave the way toward the rationalisation of the molecular features underlying the umami taste and toward the design of specific peptide-inspired compounds with specific taste properties.

Abstract Service robotics is a fast-developing sector, requiring embedded intelligence into robotic platforms to interact with the humans and the surrounding environment. One of the main challenges in the field is robust and versatile manipulation in everyday life activities. An appealing opportunity is to exploit compliant end-effectors to address the manipulation of deformable objects. However, the intrinsic compliance of such grippers results in increased difficulties in grasping control. Within the described context, this work addresses the problem of optimizing the grasping of deformable objects making use of a compliant, under-actuated, sensorless robotic hand. The main aim of the paper is, therefore, finding the best position and joint configuration for the mentioned robotic hand to grasp an unforeseen deformable object based on collected RGB image and partial point cloud. Due to the complex grasping dynamics, learning-from-simulations approaches (e.g., Reinforcement Learning) are not effective in the faced context. Thus, trial-and-error-based methodologies have to be exploited. In order to save resources, a samples-efficient approach has to be employed. Indeed, a Bayesian approach to address the optimization of the grasping strategy is proposed, enhancing it with transfer learning capabilities to exploit the acquired knowledge to grasp (partially) new objects. A PAL Robotics TIAGo (a mobile manipulator with a 7-degrees-of-freedom arm and an anthropomorphic underactuated compliant hand) has been used as a test platform, executing a pouring task while manipulating plastic (i.e., deformable) bottles. The sampling efficiency of the data-driven learning is shown, compared to an evenly spaced grid sampling of the input space. In addition, the generalization capability of the optimized model is tested (exploiting transfer learning) on a set of plastic bottles and other liquid containers, achieving a success rate of the 88%.

Perception of taste is an emergent phenomenon arising from complex molecular interactions between chemical compounds and specific taste receptors. Among all the taste perceptions, the dichotomy of sweet and bitter tastes has been the subject of several machine learning studies for classification purposes. While previous studies have provided accurate sweeteners/bitterants classifiers, there is ample scope to enhance these models by enriching the understanding of the molecular basis of bitter-sweet tastes. Towards these goals, our study focuses on the development and testing of several machine learning strategies coupled with the novel SHapley Additive exPlanations (SHAP) for a rational sweetness/bitterness classification. This allows the identification of the chemical descriptors of interest by allowing a more informed approach toward the rational design and screening of sweeteners/bitterants. To support future research in this field, we make all datasets and machine learning models publicly available and present an easy-to-use code for bitter-sweet taste prediction.

Intelligent interaction control is required in many fields of application, in which different operative situations have to be faced with different controllers. Being able to switch between optimized controllers is, indeed, of extreme importance to maximize the task performance in the different operative conditions (i.e., free-space motion and contact), especially when considering sensorless robots. To deal with the proposed context, a sensorless optimal switching impact/force (OSIF) controller is proposed. The low-level robot control is composed of an inner joint position controller, fed by an outer Cartesian impedance controller with a reference position. The estimation of the external wrench is implemented by means of an Extended Kalman Filter (EKF). The high-level controller (feeding the Cartesian impedance controller with the setpoint) is composed of an optimized impact controller (LQR-based controller), an optimized force controller (SDRE-based controller), and a continuous switching mechanism (Fuzzy Logic-based). In addition, the output of the switching mechanism is used to adapt the Cartesian impedance control parameters (i.e., stiffness and damping parameters). Experimental tests have been performed on a Franka EMIKA panda robot to validate the proposed controller. Obtained results show the capabilities of the OSIF controller, being able to detect task phase transitions while satisfying the target performance.

Abstract An algorithm for the non-intrusive disaggregation of energy consumption into its end-uses, also known as non-intrusive appliance load monitoring (NIALM), is presented. The algorithm solves an optimisation problem where the objective is to minimise the error between the total energy consumption and the sum of the individual contributions of each appliance. The algorithm assumes that a fraction of the loads present in the household is known (e.g. washing machine, dishwasher, etc.), but it also considers unknown loads, treating them as a single load. The performance of the algorithm is then compared to that obtained by two state of the art disaggregation approaches implemented in the publicly available NILMTK framework. The first one is based on Combinatorial Optimization, the second one on a Factorial Hidden Markov Model. The results show that the proposed algorithm performs satisfactorily and it even outperforms the other algorithms from some perspectives.

Many real-world tasks require multiple agents to work together. When talking about multiple agents in robotics, it is usually referenced to multiple manipulators in collaboration to solve a given task, where each one is controlled by a single agent. However, due to the increasing development of modular and re-configurable robots, it is also important to investigate the possibility of implementing multi-agent controllers that learn how to manage the manipulator’s degrees of freedom (DoF) in separated clusters for the execution of a given application (e.g., being able to face faults or, partially, new kinematics configurations). Within this context, this paper focuses on the decentralization of the robot control action learning and (re)execution considering a generic multi-DoF manipulator. Indeed, the proposed framework employs a multi-agent paradigm and investigates how such a framework impacts the control action learning process. Multiple variations of the multi-agent framework have been proposed and tested in this research, comparing the achieved performance w.r.t. a centralized (i.e., single-agent) control action learning framework, previously proposed by some of the authors. As a case study, a manipulation task (i.e., grasping and lifting) of an unknown object (to the robot controller) has been considered for validation, employing a Franka EMIKA panda robot. The MuJoCo environment has been employed to implement and test the proposed multi-agent framework. The achieved results show that the proposed decentralized approach is capable of accelerating the learning process at the beginning with respect to the single-agent framework while also reducing the computational effort. In fact, when decentralizing the controller, it is shown that the number of variables involved in the action space can be efficiently separated into several groups and several agents. This simplifies the original complex problem into multiple ones, efficiently improving the task learning process.

This paper presents the intrinsic limit determination algorithm (ILD Algorithm), a novel technique to determine the best possible performance, measured in terms of the AUC (area under the ROC curve) and accuracy, that can be obtained from a specific dataset in a binary classification problem with categorical features regardless of the model used. This limit, namely, the Bayes error, is completely independent of any model used and describes an intrinsic property of the dataset. The ILD algorithm thus provides important information regarding the prediction limits of any binary classification algorithm when applied to the considered dataset. In this paper, the algorithm is described in detail, its entire mathematical framework is presented and the pseudocode is given to facilitate its implementation. Finally, an example with a real dataset is given.

Industrial robots are commonly used to perform interaction tasks (such as assemblies or polishing), requiring the robot to be in contact with the surrounding environment. Such environments are (partially) unknown to the robot controller. Therefore, there is the need to implement interaction controllers capable of suitably reacting to the established contacts. Although standard force controllers require force/torque measurements to close the loop, most of the industrial manipulators do not have installed force/torque sensor(s). In addition, the integration of external sensors results in additional costs and implementation effort, not affordable in many contexts/applications. To extend the use of compliant controllers to sensorless interaction control, a model-based methodology is presented in this paper for the online estimation of the interaction wrench, implementing a 6D virtual sensor. Relying on sensorless Cartesian impedance control, an Extended Kalman Filter (EKF) is proposed for the interaction wrench estimation. The described approach has been validated in simulations, taking into account four different scenarios. In addition, experimental validation has been performed employing a Franka EMIKA panda robot. A human–robot interaction scenario and an assembly task have been considered to show the capabilities of the developed EKF, which is able to perform the estimation with high bandwidth, achieving convergence with limited errors.