A survey on neurosymbolic RL and planning

K. Acharya, W. Raza, C. Dourado, A. Velasquez and H. H. Song, Neurosymbolic Reinforcement Learning and Planning: A Survey, IEEE Transactions on Artificial Intelligence, vol. 5, no. 5, pp. 1939-1953, May 2024 DOI: 10.1109/TAI.2023.3311428.

The area of neurosymbolic artificial intelligence (Neurosymbolic AI) is rapidly developing and has become a popular research topic, encompassing subfields, such as neurosymbolic deep learning and neurosymbolic reinforcement learning (Neurosymbolic RL). Compared with traditional learning methods, Neurosymbolic AI offers significant advantages by simplifying complexity and providing transparency and explainability. Reinforcement learning (RL), a long-standing artificial intelligence (AI) concept that mimics human behavior using rewards and punishment, is a fundamental component of Neurosymbolic RL, a recent integration of the two fields that has yielded promising results. The aim of this article is to contribute to the emerging field of Neurosymbolic RL by conducting a literature survey. Our evaluation focuses on the three components that constitute Neurosymbolic RL: neural, symbolic, and RL. We categorize works based on the role played by the neural and symbolic parts in RL, into three taxonomies: learning for reasoning, reasoning for learning, and learning–reasoning. These categories are further divided into subcategories based on their applications. Furthermore, we analyze the RL components of each research work, including the state space, action space, policy module, and RL algorithm. In addition, we identify research opportunities and challenges in various applications within this dynamic field.

Ultrasounds as an interface to read neuro-muscular signals

X. Yang, C. Castellini, D. Farina and H. Liu, Ultrasound as a Neurorobotic Interface: A Review, IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 54, no. 6, pp. 3534-3546, June 2024 DOI: 10.1109/TSMC.2024.3358960.

Neurorobotic devices, such as prostheses, exoskeletons, and muscle stimulators, can partly restore motor functions in individuals with disabilities, such as stroke, spinal cord injury (SCI), and amputations and musculoskeletal impairments. These devices require information transfer from and to the nervous system by neurorobotic interfaces. However, current interfacing systems have limitations of low-spatial and temporal resolution, and lack robustness, with sensitivity to, e.g., fatigue and sensor displacement. Muscle scanning and imaging by ultrasound technology has emerged as a neurorobotic interface alternative to more conventional electrophysiological recordings. While muscle ultrasound detects movement of muscle fibers, and therefore does not directly detect neural information, the muscle fibers are activated by neurons in the spinal cord and therefore their motions mirror the neural code sent from the spinal cord to muscles. In this view, muscle imaging by ultrasound provides information on the neural activation underlying movement intent and execution. Here, we critically review the literature on ultrasound applied as a neurorobotic interface, focusing on technological progresses and current achievements, machine learning algorithms, and applications in both upper- and lower- limb robotics. This critical review reveals that ultrasound in the human-machine interface field has evolved from bulky hardware to miniaturized systems, from multichannel imaging to sparse channel sensing, from simple muscle morphological analysis to input signal for musculoskeletal models and machine learning, from unimodal sensing to multimodal fusion, and from conventional statistical learning to deep learning. For future advances, we recommend exploring high-precision ultrasound imaging technology, improving the wearability and ergonomics of systems and transducers, and developing user-friendly real-time human-machine interaction models.

An alternative conceptual basis for curiosity / motivation

Francesco Poli, Jill X. O’Reilly, Rogier B. Mars, Sabine Hunnius, Curiosity and the dynamics of optimal exploration, Trends in Cognitive Sciences, Volume 28, Issue 5, 2024, DOI: 10.1016/j.tics.2024.02.001.

What drives our curiosity remains an elusive and hotly debated issue, with multiple hypotheses proposed but a cohesive account yet to be established. This review discusses traditional and emergent theories that frame curiosity as a desire to know and a drive to learn, respectively. We adopt a model-based approach that maps the temporal dynamics of various factors underlying curiosity-based exploration, such as uncertainty, information gain, and learning progress. In so doing, we identify the limitations of past theories and posit an integrated account that harnesses their strengths in describing curiosity as a tool for optimal environmental exploration. In our unified account, curiosity serves as a ‘common currency’ for exploration, which must be balanced with other drives such as safety and hunger to achieve efficient action.

A novel RL setting for non-Markovian systems

Ronen I. Brafman, Giuseppe De Giacomo, Regular decision processes, Artificial Intelligence, Volume 331, 2024 DOI: 10.1016/j.artint.2024.104113.

We introduce and study Regular Decision Processes (RDPs), a new, compact model for domains with non-Markovian dynamics and rewards, in which the dependence on the past is regular, in the language theoretic sense. RDPs are an intermediate model between MDPs and POMDPs. They generalize k-order MDPs and can be viewed as a POMDP in which the hidden state is a regular function of the entire history. In factored RDPs, transition and reward functions are specified using formulas in linear temporal logics over finite traces, or using regular expressions. This allows specifying complex dependence on the past using intuitive and compact formulas, and building models of partially observable domains without specifying an underlying state space.

The problem of incorporating novelties into the knowledge of an AI agent

Shivam Goel, Panagiotis Lymperopoulos, Ravenna Thielstrom, Evan Krause, Patrick Feeney, Pierrick Lorang, Sarah Schneider, Yichen Wei, Eric Kildebeck, Stephen Goss, Michael C. Hughes, Liping Liu, Jivko Sinapov, Matthias Scheutz, A neurosymbolic cognitive architecture framework for handling novelties in open worlds, Artificial Intelligence, Volume 331, 2024 DOI: 10.1016/j.artint.2024.104111.

“Open world” environments are those in which novel objects, agents, events, and more can appear and contradict previous understandings of the environment. This runs counter to the “closed world” assumption used in most AI research, where the environment is assumed to be fully understood and unchanging. The types of environments AI agents can be deployed in are limited by the inability to handle the novelties that occur in open world environments. This paper presents a novel cognitive architecture framework to handle open-world novelties. This framework combines symbolic planning, counterfactual reasoning, reinforcement learning, and deep computer vision to detect and accommodate novelties. We introduce general algorithms for exploring open worlds using inference and machine learning methodologies to facilitate novelty accommodation. The ability to detect and accommodate novelties allows agents built on this framework to successfully complete tasks despite a variety of novel changes to the world. Both the framework components and the entire system are evaluated in Minecraft-like simulated environments. Our results indicate that agents are able to efficiently complete tasks while accommodating “concealed novelties” not shared with the architecture development team.

Imitating physiological processes for achieving robot-human social interaction

Marcos Maroto-Gómez, Martín Bueno-Adrada, María Malfaz, Álvaro Castro-González, Miguel Ángel Salichs, Human–robot pair-bonding from a neuroendocrine perspective: Modeling the effect of oxytocin, arginine vasopressin, and dopamine on the social behavior of an autonomous robot, Robotics and Autonomous Systems, Volume 176, 2024 DOI: 10.1016/j.robot.2024.104687.

Robots and humans coexist in various social environments. In these contexts, robots predominantly serve as assistants, necessitating communication and understanding capabilities. This paper introduces a biologically inspired model grounded on neuroendocrine substances that facilitate the development of social bonds between robots and individuals. The model simulates the effects of oxytocin, arginine vasopressin, and dopamine on social behavior, acting as modulators for bonding in the interaction between the social robot Mini and its users. Neuroendocrine levels vary in response to circadian rhythms and social stimuli perceived by the robot. If users express care for the robot, a positive bond is established, enhancing human–robot interaction by prompting the robot to engage in cooperative actions such as playing or communicating more frequently. Conversely, mistreating the robot leads to a deterioration of the relationship, causing user rejection. An experimenter-robot interaction scenario illustrates the model’s adaptive mechanisms involving three types of profiles: Friendly, Aversive, and Naive. Besides, a user study with 22 participants was conducted to analyze the differences in Attachment, Social Presence, perceived Anthropomorphism, Likability, and User Experience between a robot randomly selecting its behavior and a robot behaving using the bioinspired pair-bonded method proposed in this contribution. The results show how the pair-bonding with the user regulates the robot’s social behavior in response to user actions. The user study reveals statistical differences favoring the robot using the pair-bonding regulation in Attachment and Social Presence. A qualitative study using an interview-like form suggests the positive effects of creating bonds with bioinspired robots.

Interesting testing (simulated) bed for quadrotors

Júnio Santos Bulhões, Cristiane Lopes Martins, Cristian Hansen, Márcio Rodrigues da Cunha Reis, Alana da Silva Magalhães, Antonio Paulo Coimbra, Wesley Pacheco Calixto, Platform and simulator with three degrees of freedom for testing quadcopters, Robotics and Autonomous Systems, Volume 176, 2024 DOI: 10.1016/j.robot.2024.104682.

This study aims to design a test platform for quadcopters, which allows the execution of all rotational movements and prevents translational movements without affecting the dynamics of the system. The methodological approach involves both simulation and the construction of the test platform. Two simulators are developed: (i) a linear simulator, used to assist in determining control parameters, and (ii) a nonlinear simulator, used to model the nonlinearity inherent to the rotational behavior of aircraft. In addition, the control system for the quadcopter is implemented, utilizing proportional, integral, and derivative control principles. By conducting seven experiments on the test platform and in the nonlinear simulator, the obtained results are compared in order to validate the proposed methodology. The mean discrepancy observed between the mean absolute difference obtained by the test platform and by the nonlinear simulator for the angle ϕ was 0.85°, for the angle θ was 2.77°, and for the angle ψ was 4.66°. When analyzed separately, the mean absolute errors for the angles, using the nonlinear simulator and the test platform, showed differences below 2% in almost all evaluated experiments. The developed test platform preserves the rotational dynamics of the quadcopter as desired, closely approaching the results obtained by the nonlinear simulator. Consequently, this platform can be used to carry out practical tests in a controlled environment.

Interesting improvements in MC localization

Alireza Mohseni, Vincent Duchaine, Tony Wong, Improvement in Monte Carlo localization using information theory and statistical approaches, Engineering Applications of Artificial Intelligence, Volume 131, 2024 DOI: 10.1016/j.engappai.2024.107897.

Monte Carlo localization methods deploy a particle filter to resolve a hidden Markov process based on recursive Bayesian estimation, which approximates the internal states of a dynamic system given observation data. When the observed data are corrupted by outliers, the particle filter’s performance may deteriorate, preventing the algorithm from accurately computing dynamic system states such as a robot’s position, which in turn reduces the accuracy of the localization and navigation. In this paper, the notion of information entropy is used to identify outliers. Then, a probability-based approach is used to remove the discovered outliers. In addition, a new mutation process is added to the localization algorithm to exploit the posterior probability density function in order to actively detect the high-likelihood region. The goal of incorporating the mutation operator into this method is to solve the problem of algorithm impoverishment which is due to insufficient representation of the complete probability density function. Simulation experiments are used to confirm the effectiveness of the proposed techniques. They also are employed to predict the remaining viability of a lithium-ion battery. Furthermore, in an experimental study, the modified Monte Carlo localization algorithm was applied to a mobile robot to demonstrate the local planner’s improved accuracy. The test results indicate that developed techniques are capable of effectively capturing the dynamic behavior of a system and accurately tracking its characteristics.

What attention is (from a cognitive science point of view)

Wayne Wu, We know what attention is!, Trends in Cognitive Sciences, Volume 28, Issue 4, 2024 DOI: 10.1016/j.tics.2023.11.007.

Attention is one of the most thoroughly investigated psychological phenomena, yet skepticism about attention is widespread: we do not know what it is, it is too many things, there is no such thing. The deficiencies highlighted are not about experimental work but the adequacy of the scientific theory of attention. Combining common scientific claims about attention into a single theory leads to internal inconsistency. This paper demonstrates that a specific functional conception of attention is incorporated into the tasks used in standard experimental paradigms. In accepting these paradigms as valid probes of attention, we commit to this common conception. The conception unifies work at multiple levels of analysis into a coherent scientific explanation of attention. Thus, we all know what attention is.

On how much imagery can be said to be real or not by the human brain

Rebecca Keogh, Reality check: how do we know what’s real?, Trends in Cognitive Sciences, Volume 28, Issue 4, 2024 DOI: 10.1016/j.tics.2023.06.001.

How do we know what is real and what is merely a figment of our imagination? Dijkstra and Fleming tackle this question in a recent study. In contrast to the classic Perky effect, they found that once imagery crosses a ‘reality threshold’, it becomes difficult to distinguish from reality.