Background: Value alignment in computer science research is often used to refer to the process of aligning artificial intelligence with humans, but the way the phrase is used often lacks precision. Objectives: In this paper, we conduct a systematic literature review to advance the understanding of value alignment in artificial intelligence by characterising the topic in the context of its research literature. We use this to suggest a more precise definition of the term. Methods: We analyse 172 value alignment research articles that have been published in recent years and synthesise their content using thematic analyses. Results: Our analysis leads to six themes: value alignment drivers & approaches; challenges in value alignment; values in value alignment; cognitive processes in humans and AI; human-agent teaming; and designing and developing value-aligned systems. Conclusions: By analysing these themes in the context of the literature we define value alignment as an ongoing process between humans and autonomous agents that aims to express and implement abstract values in diverse contexts, while managing the cognitive limits of both humans and AI agents and also balancing the conflicting ethical and political demands generated by the values in different groups. Our analysis gives rise to a set of research challenges and opportunities in the field of value alignment for future work.

LLMs have recently been used to generate Python programs representing generalized plans in PDDL planning, i.e., plans that generalize across the tasks of a given PDDL domain. Previous work proposed a framework consisting of three steps: the LLM first generates a summary and then a strategy for the domain, both in natural language, and then implements that strategy as a Python program, that gets debugged on example planning tasks. In that work, only one strategy is generated and passed directly to the program generation. If the strategy is incorrect, its implementation will therefore result in an incorrect generalized plan. Here, we introduce an approach that generates the strategy in the form of pseudocode and enables automatic debugging of the pseudocode, hence allowing us to identify and fix errors prior to the generation of the generalized plan itself. Additionally, we extend the Python debugging phase with a reflection step prompting the LLM to pinpoint the reason for the observed plan failure. Finally, we take inspiration from LLM code generation to produce several program variants and pick the best one. Running experiments on 17 benchmark domains, we show that these extensions substantially improve (and never deteriorate) the quality of the generalized plans. In 12 of the domains, our best Python programs solve all tasks that can be generated with the respective instance generator.

The objective is to find a Cellular Automata (CA) rule that can evolve 2D patterns that are optimal with respect to a global fitness function. The global fitness is defined as the sum of local computed utilities. A utility or value function computes a score depending on the states in the local neighborhood. First the method is explained that was followed to find such a CA rule. Then this method is applied to find a rule that maximizes social wealth. Here wealth is defined as the sum of the payoffs that all players (agents, cells) receive in a prisoner's dilemma game, and then shared equally among them. The problem is solved in four steps: (0) Defining the utility function, (1) Finding optimal master patterns with a Genetic Algorithm, (2) Extracting templates (local neighborhood configurations), (3) Inserting the templates in a general CA rule. The constructed CA rule finds optimal and near-optimal patterns for even and odd grid sizes. Optimal patterns of odd size contain exactly one singularity, a 2 x 2 block of cooperators.

Domain-independent heuristics have long been a cornerstone of AI planning, offering general solutions applicable across a wide range of tasks without requiring domain-specific engineering. However, the advent of large language models (LLMs) presents an opportunity to generate heuristics tailored to specific planning problems, potentially challenging the necessity of domain independence as a strict design principle. In this paper, we explore the use of LLMs to automatically derive planning heuristics from task descriptions represented as successor generators and goal tests written in general purpose programming language. We investigate the trade-offs between domain-specific LLM-generated heuristics and traditional domain-independent methods in terms of computational efficiency and explainability. Our experiments demonstrate that LLMs can create heuristics that achieve state-of-the-art performance on some standard IPC domains, as well as their ability to solve problems that lack an adequate Planning Domain Definition Language ({\sc pddl}) representation. We discuss whether these results signify a paradigm shift and how they can complement existing approaches.

The measurement of deep water gravity wave elevations using in-situ devices, such as wave gauges, typically yields spatially sparse data. This sparsity arises from the deployment of a limited number of gauges due to their installation effort and high operational costs. The reconstruction of the spatio-temporal extent of surface elevation poses an ill-posed data assimilation problem, challenging to solve with conventional numerical techniques. To address this issue, we propose the application of a physics-informed neural network (PINN), aiming to reconstruct physically consistent wave fields between two designated measurement locations several meters apart. Our method ensures this physical consistency by integrating residuals of the hydrodynamic nonlinear Schr\"{o}dinger equation (NLSE) into the PINN's loss function. Using synthetic wave elevation time series from distinct locations within a wave tank, we initially achieve successful reconstruction quality by employing constant, predetermined NLSE coefficients. However, the reconstruction quality is further improved by introducing NLSE coefficients as additional identifiable variables during PINN training. The results not only showcase a technically relevant application of the PINN method but also represent a pioneering step towards improving the initialization of deterministic wave prediction methods.

We study the performance of state-of-the-art human keypoint detectors in the context of close proximity human-robot interaction. The detection in this scenario is specific in that only a subset of body parts such as hands and torso are in the field of view. In particular, (i) we survey existing datasets with human pose annotation from the perspective of close proximity images and prepare and make publicly available a new Human in Close Proximity (HiCP) dataset; (ii) we quantitatively and qualitatively compare state-of-the-art human whole-body 2D keypoint detection methods (OpenPose, MMPose, AlphaPose, Detectron2) on this dataset; (iii) since accurate detection of hands and fingers is critical in applications with handovers, we evaluate the performance of the MediaPipe hand detector; (iv) we deploy the algorithms on a humanoid robot with an RGB-D camera on its head and evaluate the performance in 3D human keypoint detection. A motion capture system is used as reference. The best performing whole-body keypoint detectors in close proximity were MMPose and AlphaPose, but both had difficulty with finger detection. Thus, we propose a combination of MMPose or AlphaPose for the body and MediaPipe for the hands in a single framework providing the most accurate and robust detection. We also analyse the failure modes of individual detectors -- for example, to what extent the absence of the head of the person in the image degrades performance. Finally, we demonstrate the framework in a scenario where a humanoid robot interacting with a person uses the detected 3D keypoints for whole-body avoidance maneuvers.

Touch is a key part of interaction and communication between humans, but has still been little explored in human-robot interaction. In this work, participants were asked to approach and touch a humanoid robot on the hand (Nao - 26 participants; Pepper - 28 participants) to get its attention. We designed reaction behaviors for the robot that consisted in four different combinations of arm movements with the touched hand moving forward or back and the other hand moving forward or staying in place, with simultaneous leaning back, followed by looking at the participant. We studied which reaction of the robot people found the most appropriate and what was the reason for their choice. For both robots, the preferred reaction of the robot hand being touched was moving back. For the other hand, no movement at all was rated most natural for the Pepper, while it was movement forward for the Nao. A correlation between the anxiety subscale of the participants' personality traits and the passive to active/aggressive nature of the robot reactions was found. Most participants noticed the leaning back and rated it positively. Looking at the participant was commented on positively by some participants in unstructured comments. We also analyzed where and how participants spontaneously touched the robot on the hand. In summary, the touch reaction behaviors designed here are good candidates to be deployed more generally in social robots, possibly including incidental touch in crowded environments. The robot size constitutes one important factor shaping how the robot reaction is perceived.

Goal recognition is an important problem in many application domains (e.g., pervasive computing, intrusion detection, computer games, etc.). In many application scenarios it is important that goal recognition algorithms can recognize goals of an observed agent as fast as possible and with minimal domain knowledge. Hence, in this paper, we propose a hybrid method for online goal recognition that combines a symbolic planning landmark based approach and a data-driven goal recognition approach and evaluate it in a real-world cooking scenario. The empirical results show that the proposed method is not only significantly more efficient in terms of computation time than the state-of-the-art but also improves goal recognition performance. Furthermore, we show that the utilized planning landmark based approach, which was so far only evaluated on artificial benchmark domains, achieves also good recognition performance when applied to a real-world cooking scenario.

Humans and animals excel in combining information from multiple sensory modalities, controlling their complex bodies, adapting to growth, failures, or using tools. These capabilities are also highly desirable in robots. They are displayed by machines to some extent. Yet, the artificial creatures are lagging behind. The key foundation is an internal representation of the body that the agent - human, animal, or robot - has developed. The mechanisms of operation of body models in the brain are largely unknown and even less is known about how they are constructed from experience after birth. In collaboration with developmental psychologists, we conducted targeted experiments to understand how infants acquire first "sensorimotor body knowledge". These experiments inform our work in which we construct embodied computational models on humanoid robots that address the mechanisms behind learning, adaptation, and operation of multimodal body representations. At the same time, we assess which of the features of the "body in the brain" should be transferred to robots to give rise to more adaptive and resilient, self-calibrating machines. We extend traditional robot kinematic calibration focusing on self-contained approaches where no external metrology is needed: self-contact and self-observation. Problem formulation allowing to combine several ways of closing the kinematic chain simultaneously is presented, along with a calibration toolbox and experimental validation on several robot platforms. Finally, next to models of the body itself, we study peripersonal space - the space immediately surrounding the body. Again, embodied computational models are developed and subsequently, the possibility of turning these biologically inspired representations into safe human-robot collaboration is studied.

We introduce HyperMorph, a framework that facilitates efficient hyperparameter tuning in learning-based deformable image registration. Classical registration algorithms perform an iterative pair-wise optimization to compute a deformation field that aligns two images. Recent learning-based approaches leverage large image datasets to learn a function that rapidly estimates a deformation for a given image pair. In both strategies, the accuracy of the resulting spatial correspondences is strongly influenced by the choice of certain hyperparameter values. However, an effective hyperparameter search consumes substantial time and human effort as it often involves training multiple models for different fixed hyperparameter values and may lead to suboptimal registration. We propose an amortized hyperparameter learning strategy to alleviate this burden by learning the impact of hyperparameters on deformation fields. We design a meta network, or hypernetwork, that predicts the parameters of a registration network for input hyperparameters, thereby comprising a single model that generates the optimal deformation field corresponding to given hyperparameter values. This strategy enables fast, high-resolution hyperparameter search at test-time, reducing the inefficiency of traditional approaches while increasing flexibility. We also demonstrate additional benefits of HyperMorph, including enhanced robustness to model initialization and the ability to rapidly identify optimal hyperparameter values specific to a dataset, image contrast, task, or even anatomical region, all without the need to retrain models. We make our code publicly available at http://hypermorph.voxelmorph.net.