Elon Musk's recent announcement of an upcoming Tesla Bot -- complete with a human form, "human-level hands" and a characteristically optimistic delivery date -- has garnered a healthy serving of criticism for good reason. Among other capabilities, Musk says, the robot will eventually be capable of running errands such as going to the grocery store alone. Boston Dynamics, which has developed the most advanced humanoid robot ever created, has spent more than a decade working on its Atlas platform. While progress has been impressive, with Atlas running, jumping and even dancing in front of tens of millions of YouTube viewers, the company is quick to acknowledge that the robot is a long way from performing complex tasks autonomously. One of the best examples of evolutionary robotics potential -- and unfulfilled promise -- goes as far back as 2010 to a study published in the PLOS Biology journal.

The generation of feasible adversarial examples is necessary for properly assessing models that work on constrained feature space. However, it remains a challenging task to enforce constraints into attacks that were designed for computer vision. We propose a unified framework to generate feasible adversarial examples that satisfy given domain constraints. Our framework supports the use cases reported in the literature and can handle both linear and non-linear constraints. We instantiate our framework into two algorithms: a gradient-based attack that introduces constraints in the loss function to maximize, and a multi-objective search algorithm that aims for misclassification, perturbation minimization, and constraint satisfaction. We show that our approach is effective on two datasets from different domains, with a success rate of up to 100%, where state-of-the-art attacks fail to generate a single feasible example. In addition to adversarial retraining, we propose to introduce engineered non-convex constraints to improve model adversarial robustness. We demonstrate that this new defense is as effective as adversarial retraining. Our framework forms the starting point for research on constrained adversarial attacks and provides relevant baselines and datasets that future research can exploit.

Automated Driving Systems (ADSs) have seen rapid progress in recent years. To ensure the safety and reliability of these systems, extensive testings are being conducted before their future mass deployment. Testing the system on the road is the closest to real-world and desirable approach, but it is incredibly costly. Also, it is infeasible to cover rare corner cases using such real-world testing. Thus, a popular alternative is to evaluate an ADS's performance in some well-designed challenging scenarios, a.k.a. scenario-based testing. High-fidelity simulators have been widely used in this setting to maximize flexibility and convenience in testing what-if scenarios. Although many works have been proposed offering diverse frameworks/methods for testing specific systems, the comparisons and connections among these works are still missing. To bridge this gap, in this work, we provide a generic formulation of scenario-based testing in high-fidelity simulation and conduct a literature review on the existing works. We further compare them and present the open challenges as well as potential future research directions.

A fitness assignment process transforms the features (such as the objective value) of a candidate solution to a scalar fitness, which then is the basis for selection. Under Frequency Fitness Assignment (FFA), the fitness corresponding to an objective value is its encounter frequency and is subject to minimization. FFA creates algorithms that are not biased towards better solutions and are invariant under all bijections of the objective function value. We investigate the impact of FFA on the performance of two theory-inspired, state-of-the-art EAs, the Greedy (2+1) GA and the Self-Adjusting (1+(lambda,lambda)) GA. FFA improves their performance significantly on some problems that are hard for them. We empirically find that one FFA-based algorithm can solve all theory-based benchmark problems in this study, including traps, jumps, and plateaus, in polynomial time. We propose two hybrid approaches that use both direct and FFA-based optimization and find that they perform well. All FFA-based algorithms also perform better on satisfiability problems than all pure algorithm variants.

Information theoretic analysis of large evolved programs produced by running genetic programming for up to a million generations has shown even functions as smooth and well behaved as floating point addition and multiplication loose entropy and consequently are robust and fail to propagate disruption to their outputs. This means, while dependent upon fitness tests, many genetic changes deep within trees are silent. For evolution to proceed at reasonable rate it must be possible to measure the impact of most code changes, yet in large trees most crossover sites are distant from the root node. We suggest to evolve very large very complex programs, it will be necessary to adopt an open architecture where most mutation sites are within 10 to 100 levels of the organism's environment.

Now scientists at the University of Vermont, Tufts University, and the Wyss Institute for Biologically Inspired Engineering at Harvard University have discovered an entirely new form of biological reproduction -- and applied their discovery to create the first-ever, self-replicating living robots. The same team that built the first living robots ("Xenobots," assembled from frog cells -- reported in 2020) has discovered that these computer-designed and hand-assembled organisms can swim out into their tiny dish, find single cells, gather hundreds of them together, and assemble "baby" Xenobots inside their Pac-Man-shaped "mouth" -- that, a few days later, become new Xenobots that look and move just like themselves. And then these new Xenobots can go out, find cells, and build copies of themselves. "With the right design -- they will spontaneously self-replicate," says Joshua Bongard, Ph.D., a computer scientist and robotics expert at the University of Vermont who co-led the new research. The results of the new research were published November 29, 2021, in the Proceedings of the National Academy of Sciences.

Over billions of years, organisms have evolved many ways of replicating, from budding plants to sexual animals to invading viruses. Now scientists at the University of Vermont, Tufts University, and the Wyss Institute for Biologically Inspired Engineering at Harvard University have discovered an entirely new form of biological reproduction--and applied their discovery to create the first-ever, self-replicating living robots. The same team that built the first living robots ("Xenobots," assembled from frog cells--reported in 2020) has discovered that these computer-designed and hand-assembled organisms can swim out into their tiny dish, find single cells, gather hundreds of them together, and assemble "baby" Xenobots inside their Pac-Man-shaped "mouth"--that, a few days later, become new Xenobots that look and move just like themselves. And then these new Xenobots can go out, find cells, and build copies of themselves. "With the right design--they will spontaneously self-replicate," says Joshua Bongard, Ph.D., a computer scientist and robotics expert at the University of Vermont who co-led the new research.

Artificial Intelligence, when amalgamated with games makes the ideal structure for research and advancing the field. Multi-agent games have multiple controls for each agent which generates huge amounts of data while increasing search complexity. Thus, we need advanced search methods to find a solution and create an artificially intelligent agent. In this paper, we propose our novel Evolutionary Monte Carlo Tree Search (FEMCTS) agent which borrows ideas from Evolutionary Algorthims (EA) and Monte Carlo Tree Search (MCTS) to play the game of Pommerman. It outperforms Rolling Horizon Evolutionary Algorithm (RHEA) significantly in high observability settings and performs almost as well as MCTS for most game seeds, outperforming it in some cases.

FCMpy is an open source package in Python for building and analyzing Fuzzy Cognitive Maps. More specifically, the package allows 1) deriving fuzzy causal weights from qualitative data, 2) simulating the system behavior, 3) applying machine learning algorithms (e.g., Nonlinear Hebbian Learning, Active Hebbian Learning, Genetic Algorithms and Deterministic Learning) to adjust the FCM causal weight matrix and to solve classification problems, and 4) implementing scenario analysis by simulating hypothetical interventions (i.e., analyzing what-if scenarios).

False alerts due to misconfigured/ compromised IDS in ICS networks can lead to severe economic and operational damage. To solve this problem, research has focused on leveraging deep learning techniques that help reduce false alerts. However, a shortcoming is that these works often require or implicitly assume the physical and cyber sensors to be trustworthy. Implicit trust of data is a major problem with using artificial intelligence or machine learning for CPS security, because during critical attack detection time they are more at risk, with greater likelihood and impact, of also being compromised. To address this shortcoming, the problem is reframed on how to make good decisions given uncertainty. Then, the decision is detection, and the uncertainty includes whether the data used for ML-based IDS is compromised. Thus, this work presents an approach for reducing false alerts in CPS power systems by dealing uncertainty without the knowledge of prior distribution of alerts. Specifically, an evidence theoretic based approach leveraging Dempster Shafer combination rules are proposed for reducing false alerts. A multi-hypothesis mass function model is designed that leverages probability scores obtained from various supervised-learning classifiers. Using this model, a location-cum-domain based fusion framework is proposed and evaluated with different combination rules, that fuse multiple evidence from inter-domain and intra-domain sensors. The approach is demonstrated in a cyber-physical power system testbed with Man-In-The-Middle attack emulation in a large-scale synthetic electric grid. For evaluating the performance, plausibility, belief, pignistic, etc. metrics as decision functions are considered. To improve the performance, a multi-objective based genetic algorithm is proposed for feature selection considering the decision metrics as the fitness function.