This volume contains the Late-Breaking Abstracts accepted at Evo* 2022 Conference, held in Madrid (Spain), from 20 to 22 of April. They were also presented as short talks as well as at the conference's poster session. The works present ongoing research and preliminary results investigating on the application of different approaches of Evolutionary Computation and other Nature-Inspired techniques to different problems, most of them real world ones. These are very promising contributions, since they outline some of the incoming advances and applications in the area of nature-inspired methods, mainly Evolutionary Algorithms.

World-renowned semiconductor producer Nvidia is widely regarded as a pioneering force behind artificial intelligence (AI), and it remains a leader in the field today. But AI is a rapidly growing industry with plenty of room for other contributors, and in fact, some experts predict the majority of companies will be using AI by 2030, adding $13 trillion in value to the global economy. Therefore, while Nvidia is a $413 billion giant today, three Motley Fool contributors think C3ai (AI -0.70%), Riskified (RSKD 0.69%), and CrowdStrike (CRWD 0.83%) are artificial intelligence powerhouses of the future. Anthony Di Pizio (C3ai): One thing the artificial intelligence industry is missing is accessibility. Typically, only large technology companies with the financial resources and the ability to attract talented developers have been able to use AI in a meaningful capacity.

Cyber-physical systems (CPSs) are smart systems that depend on the synergy of cyber and physical components. They link the physical world (e.g. through sensors, actuators, robotics, and embedded systems) with the virtual world of information processing. Applications of CPS have the tremendous potential of improving convenience, comfort, and safety in our daily life. This paper provides a brief introduction to CPSs and their applications. The term "cyber-physical system" (CPS) was coined in 2006 by Helen Gill of the US National Science Foundation (Henshaw, 2016).

Autonomous micromobility has been attracting the attention of researchers and practitioners in recent years. A key component of many micro-transport vehicles is the DC motor, a complex dynamical system that is continuous and non-linear. Learning to quickly control the DC motor in the presence of disturbances and uncertainties is desired for various applications that require robustness and stability. Techniques to accomplish this task usually rely on a mathematical system model, which is often insufficient to anticipate the effects of time-varying and interrelated sources of non-linearities. While some model-free approaches have been successful at the task, they rely on massive interactions with the system and are trained in specialized hardware in order to fit a highly parameterized controller. In this work, we learn to steer a DC motor via sample-efficient reinforcement learning. Using data collected from hardware interactions in the real world, we additionally build a simulator to experiment with a wide range of parameters and learning strategies. With the best parameters found, we learn an effective control policy in one minute and 53 seconds on a simulation and in 10 minutes and 35 seconds on a physical system.

Effective reinforcement learning requires a proper balance of exploration and exploitation defined by the dispersion of action distribution. However, this balance depends on the task, the current stage of the learning process, and the current environment state. Existing methods that designate the action distribution dispersion require problem-dependent hyperparameters. In this paper, we propose to automatically designate the action distribution dispersion using the following principle: This distribution should have sufficient dispersion to enable the evaluation of future policies. To that end, the dispersion should be tuned to assure a sufficiently high probability (densities) of the actions in the replay buffer and the modes of the distributions that generated them, yet this dispersion should not be higher. This way, a policy can be effectively evaluated based on the actions in the buffer, but exploratory randomness in actions decreases when this policy converges. The above principle is verified here on challenging benchmarks Ant, HalfCheetah, Hopper, and Walker2D, with good results. Our method makes the action standard deviations converge to values similar to those resulting from trial-and-error optimization.

Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks. Despite its success, the said paradigm is still constrained by several factors, such as (i) low-quality region proposals for novel classes and (ii) negligence of the inter-class correlation among different classes. Such limitations hinder the generalization of base-class knowledge for the detection of novel-class objects. In this work, we design Meta-DETR, which (i) is the first image-level few-shot detector, and (ii) introduces a novel inter-class correlational meta-learning strategy to capture and leverage the correlation among different classes for robust and accurate few-shot object detection. Meta-DETR works entirely at image level without any region proposals, which circumvents the constraint of inaccurate proposals in prevalent few-shot detection frameworks. In addition, the introduced correlational meta-learning enables Meta-DETR to simultaneously attend to multiple support classes within a single feedforward, which allows to capture the inter-class correlation among different classes, thus significantly reducing the misclassification over similar classes and enhancing knowledge generalization to novel classes. Experiments over multiple few-shot object detection benchmarks show that the proposed Meta-DETR outperforms state-of-the-art methods by large margins. The implementation codes are available at https://github.com/ZhangGongjie/Meta-DETR.

The composition of a macroscopic plasticity model often requires the following steps. First, there are observations of causality relations deduced by modelers to hypothesize mechanisms that lead to the plastic flow. These causality relations along with constraints inferred from physics and universally accepted principles lead to mathematical equations. For instance, the family of Gurson models employs the observation of void growth to employ the yield surface (Gurson, 1977). Crystal plasticity models relate the plastic flow with slip systems to predict the anisotropic responses of single crystals (Rice, 1971; Uchic et al., 2004; Clayton, 2010; Ma and Sun, 2020; Ma et al., 2021). Granular plasticity models propose theories that relate the fabric of force chains and porosity to the onset of plastic yielding and the resultant plastic flow (Cowin, 1985; Kuhn et al., 2015; Wang and Sun, 2018; Sun et al., 2022). Finally, the mathematical equations are then either used directly in engineering analysis and designs (e.g. the Mohr-Coulomb envelope) or are incorporated into a boundary value problem in which the approximation solution can be obtained from a partial differential equation solver that provides incremental updates of stress-strain relations. However, a subtle but significant limitation of this paradigm is that it imposes the burdens on modelers of being able to describe the mechanisms verbally via terminologies or atomic facts (cf.

This paper introduces SCALER, a quadrupedal robot that demonstrates climbing on bouldering walls, overhangs, ceilings and trotting on the ground. SCALER is one of the first high-degrees of freedom four-limbed robots that can free-climb under the Earth's gravity and one of the most mechanically efficient quadrupeds on the ground. Where other state-of-the-art climbers specialize in climbing, SCALER promises practical free-climbing with payload \textit{and} ground locomotion, which realizes true versatile mobility. A new climbing gait, SKATE gait, increases the payload by utilizing the SCALER body linkage mechanism. SCALER achieves a maximum normalized locomotion speed of $1.87$ /s, or $0.56$ m/s on the ground and $1.0$ /min, or $0.35$ m/min in bouldering wall climbing. Payload capacity reaches $233$ % of the SCALER weight on the ground and $35$ % on the vertical wall. Our GOAT gripper, a mechanically adaptable underactuated two-finger gripper, successfully grasps convex and non-convex objects and supports SCALER.

In today's era of smart cyber-physical systems, Deep Neural Networks (DNNs) have become ubiquitous due to their state-of-the-art performance in complex real-world applications. The high computational complexity of these networks, which translates to increased energy consumption, is the foremost obstacle towards deploying large DNNs in resource-constrained systems. Fixed-Point (FP) implementations achieved through post-training quantization are commonly used to curtail the energy consumption of these networks. However, the uniform quantization intervals in FP restrict the bit-width of data structures to large values due to the need to represent most of the numbers with sufficient resolution and avoid high quantization errors. In this paper, we leverage the key insight that (in most of the scenarios) DNN weights and activations are mostly concentrated near zero and only a few of them have large magnitudes. We propose CoNLoCNN, a framework to enable energy-efficient low-precision deep convolutional neural network inference by exploiting: (1) non-uniform quantization of weights enabling simplification of complex multiplication operations; and (2) correlation between activation values enabling partial compensation of quantization errors at low cost without any run-time overheads. To significantly benefit from non-uniform quantization, we also propose a novel data representation format, Encoded Low-Precision Binary Signed Digit, to compress the bit-width of weights while ensuring direct use of the encoded weight for processing using a novel multiply-and-accumulate (MAC) unit design.

Analogue deep learning, a new branch of artificial intelligence, promises faster computation with less energy consumption.