In this work, we argue that the search for Artificial General Intelligence (AGI) should start from a much lower level than human-level intelligence. The circumstances of intelligent behavior in nature resulted from an organism interacting with its surrounding environment, which could change over time and exert pressure on the organism to allow for learning of new behaviors or environment models. Our hypothesis is that learning occurs through interpreting sensory feedback when an agent acts in an environment. For that to happen, a body and a reactive environment are needed. We evaluate a method to evolve a biologically-inspired artificial neural network that learns from environment reactions named Neuroevolution of Artificial General Intelligence (NAGI), a framework for low-level AGI. This method allows the evolutionary complexification of a randomly-initialized spiking neural network with adaptive synapses, which controls agents instantiated in mutable environments. Such a configuration allows us to benchmark the adaptivity and generality of the controllers. The chosen tasks in the mutable environments are food foraging, emulation of logic gates, and cart-pole balancing. The three tasks are successfully solved with rather small network topologies and therefore it opens up the possibility of experimenting with more complex tasks and scenarios where curriculum learning is beneficial.

Hyperparameter optimization constitutes a large part of typical modern machine learning workflows. This arises from the fact that machine learning methods and corresponding preprocessing steps often only yield optimal performance when hyperparameters are properly tuned. But in many applications, we are not only interested in optimizing ML pipelines solely for predictive accuracy; additional metrics or constraints must be considered when determining an optimal configuration, resulting in a multi-objective optimization problem. This is often neglected in practice, due to a lack of knowledge and readily available software implementations for multi-objective hyperparameter optimization. In this work, we introduce the reader to the basics of multi-objective hyperparameter optimization and motivate its usefulness in applied ML. Furthermore, we provide an extensive survey of existing optimization strategies, both from the domain of evolutionary algorithms and Bayesian optimization. We illustrate the utility of MOO in several specific ML applications, considering objectives such as operating conditions, prediction time, sparseness, fairness, interpretability and robustness.

To address the trade-off problem of quality-diversity for the generated images in imbalanced classification tasks, we research on over-sampling based methods at the feature level instead of the data level and focus on searching the latent feature space for optimal distributions. On this basis, we propose an iMproved Estimation Distribution Algorithm based Latent featUre Distribution Evolution (MEDA LUDE) algorithm, where a joint learning procedure is programmed to make the latent features both optimized and evolved by the deep neural networks and the evolutionary algorithm, respectively. We explore the effect of the Large-margin Gaussian Mixture (L-GM) loss function on distribution learning and design a specialized fitness function based on the similarities among samples to increase diversity. Extensive experiments on benchmark based imbalanced datasets validate the effectiveness of our proposed algorithm, which can generate images with both quality and diversity. Furthermore, the MEDA LUDE algorithm is also applied to the industrial field and successfully alleviates the imbalanced issue in fabric defect classification.

This paper presents an optimal motion planning framework to generate versatile energy-optimal quadrupedal jumping motions automatically (e.g., flips, spin). The jumping motions via the centroidal dynamics are formulated as a 12-dimensional black-box optimization problem subject to the robot kino-dynamic constraints. Gradient-based approaches offer great success in addressing trajectory optimization (TO), yet, prior knowledge (e.g., reference motion, contact schedule) is required and results in sub-optimal solutions. The new proposed framework first employed a heuristics-based optimization method to avoid these problems. Moreover, a prioritization fitness function is created for heuristics-based algorithms in robot ground reaction force (GRF) planning, enhancing convergence and searching performance considerably. Since heuristics-based algorithms often require significant time, motions are planned offline and stored as a pre-motion library. A selector is designed to automatically choose motions with user-specified or perception information as input. The proposed framework has been successfully validated only with a simple continuously tracking PD controller in an open-source Mini-Cheetah by several challenging jumping motions, including jumping over a window-shaped obstacle with 30 cm height and left-flipping over a rectangle obstacle with 27 cm height.

Swarm learning is one of the latest in a series of buzzwords that seem to continually appear. Along with artificial intelligence and machine learning, this latest phrase seems to be getting more and more "out there." Let's go deeper and find out… The name swarm learning was inspired by the collective behavior of animals and insects that come together to achieve a mutual goal. Think of bees swarming to build a hive, small fish forming a bait ball to scare off larger predator fish, wolves hunting their prey in packs, or birds moving together in flight. By joining together, insects and animals pool their resources and work together to collectively increase their ability to accomplish a goal.

This work utilizes a particle swarm optimizer (PSO) for initial orbit determination for a chief and deputy scenario in the circular restricted three-body problem (CR3BP). The PSO is used to minimize the difference between actual and estimated observations and knowledge of the chief's position with known CR3BP dynamics to determine the deputy's initial state. Convergence is achieved through limiting particle starting positions to feasible positions based on the known chief position, and sensor constraints. Parallel and GPU processing methods are used to improve computation time and provide an accurate initial state estimate for a variety of cislunar orbit geometries.

Amphibious ground-aerial vehicles fuse flying and driving modes to enable more flexible air-land mobility and have received growing attention recently. By analyzing the existing amphibious vehicles, we highlight the autonomous fly-driving functionality for the effective uses of amphibious vehicles in complex three-dimensional urban transportation systems. We review and summarize the key enabling technologies for intelligent flying-driving in existing amphibious vehicle designs, identify major technological barriers and propose potential solutions for future research and innovation. This paper aims to serve as a guide for research and development of intelligent amphibious vehicles for urban transportation toward the future.

Particle-based modeling of materials at atomic scale plays an important role in the development of new materials and understanding of their properties. The accuracy of particle simulations is determined by interatomic potentials, which allow to calculate the potential energy of an atomic system as a function of atomic coordinates and potentially other properties. First-principles-based ab initio potentials can reach arbitrary levels of accuracy, however their aplicability is limited by their high computational cost. Machine learning (ML) has recently emerged as an effective way to offset the high computational costs of ab initio atomic potentials by replacing expensive models with highly efficient surrogates trained on electronic structure data. Among a plethora of current methods, symbolic regression (SR) is gaining traction as a powerful "white-box" approach for discovering functional forms of interatomic potentials. This contribution discusses the role of symbolic regression in Materials Science (MS) and offers a comprehensive overview of current methodological challenges and state-of-the-art results. A genetic programming-based approach for modeling atomic potentials from raw data (consisting of snapshots of atomic positions and associated potential energy) is presented and empirically validated on ab initio electronic structure data.

Task allocation using a team or coalition of robots is one of the most important problems in robotics, computer science, operational research, and artificial intelligence. In recent work, research has focused on handling complex objectives and feasibility constraints amongst other variations of the multi-robot task allocation problem. There are many examples of important research progress in these directions. We present a general formulation of the task allocation problem that generalizes several versions that are well-studied. Our formulation includes the states of robots, tasks, and the surrounding environment in which they operate. We describe how the problem can vary depending on the feasibility constraints, objective functions, and the level of dynamically changing information. In addition, we discuss existing solution approaches for the problem including optimization-based approaches, and market-based approaches.

We devise a 3D scene graph representation, contact graph+ (cg+), for efficient sequential task planning. Augmented with predicate-like attributes, this contact graph-based representation abstracts scene layouts with succinct geometric information and valid robot-scene interactions. Goal configurations, naturally specified on contact graphs, can be produced by a genetic algorithm with a stochastic optimization method. A task plan is then initialized by computing the Graph Editing Distance (GED) between the initial contact graphs and the goal configurations, which generates graph edit operations corresponding to possible robot actions. We finalize the task plan by imposing constraints to regulate the temporal feasibility of graph edit operations, ensuring valid task and motion correspondences. In a series of simulations and experiments, robots successfully complete complex sequential object rearrangement tasks that are difficult to specify using conventional planning language like Planning Domain Definition Language (PDDL), demonstrating the high feasibility and potential of robot sequential task planning on contact graph.