China leads the world in 37 out of 44 critical technologies, with Western democracies falling behind in the race for scientific and research breakthroughs, a report by an Australian think tank has found. China is in a position to become the world's top technology superpower, with its dominance already spanning defence, space, robotics, energy, the environment, biotechnology, artificial intelligence (AI), advanced materials and key quantum technology, according to the report by the Australian Strategic Policy Institute (ASPI). The key areas dominated by China include drones, machine learning, electric batteries, nuclear energy, photovoltaics, quantum sensors and critical minerals extraction, according to the Critical Technology Tracker released on Thursday. China's dominance in some fields is so entrenched that all of the world's top 10 leading research institutions for certain technologies are located in the country, according to ASPI. In comparison, the United States leads in just seven critical technologies, including space launch systems and quantum computing, according to ASPI, which receives funding from the Australian, United Kingdom and US governments, as well as private sector sources including the defence and tech industries.

Neither deep neural networks nor symbolic AI alone has approached the kind of intelligence expressed in humans. This is mainly because neural networks are not able to decompose joint representations to obtain distinct objects (the so-called binding problem), while symbolic AI suffers from exhaustive rule searches, among other problems. These two problems are still pronounced in neuro-symbolic AI which aims to combine the best of the two paradigms. Here, we show that the two problems can be addressed with our proposed neuro-vector-symbolic architecture (NVSA) by exploiting its powerful operators on high-dimensional distributed representations that serve as a common language between neural networks and symbolic AI. The efficacy of NVSA is demonstrated by solving the Raven's progressive matrices datasets. Compared to state-of-the-art deep neural network and neuro-symbolic approaches, end-to-end training of NVSA achieves a new record of 87.7% average accuracy in RAVEN, and 88.1% in I-RAVEN datasets. Moreover, compared to the symbolic reasoning within the neuro-symbolic approaches, the probabilistic reasoning of NVSA with less expensive operations on the distributed representations is two orders of magnitude faster. Our code is available at https://github.com/IBM/neuro-vector-symbolic-architectures.

The long runtime of high-fidelity partial differential equation (PDE) solvers makes them unsuitable for time-critical applications. We propose to accelerate PDE solvers using reduced-order modeling (ROM). Whereas prior ROM approaches reduce the dimensionality of discretized vector fields, our continuous reduced-order modeling (CROM) approach builds a low-dimensional embedding of the continuous vector fields themselves, not their discretization. We represent this reduced manifold using continuously differentiable neural fields, which may train on any and all available numerical solutions of the continuous system, even when they are obtained using diverse methods or discretizations. We validate our approach on an extensive range of PDEs with training data from voxel grids, meshes, and point clouds. Compared to prior discretization-dependent ROM methods, such as linear subspace proper orthogonal decomposition (POD) and nonlinear manifold neural-network-based autoencoders, CROM features higher accuracy, lower memory consumption, dynamically adaptive resolutions, and applicability to any discretization. For equal latent space dimension, CROM exhibits 79$\times$ and 49$\times$ better accuracy, and 39$\times$ and 132$\times$ smaller memory footprint, than POD and autoencoder methods, respectively. Experiments demonstrate 109$\times$ and 89$\times$ wall-clock speedups over unreduced models on CPUs and GPUs, respectively. Videos and codes are available on the project page: https://crom-pde.github.io

Reinforcement learning (RL) has recently proven great success in various domains. Yet, the design of the reward function requires detailed domain expertise and tedious fine-tuning to ensure that agents are able to learn the desired behaviour. Using a sparse reward conveniently mitigates these challenges. However, the sparse reward represents a challenge on its own, often resulting in unsuccessful training of the agent. In this paper, we therefore address the sparse reward problem in RL. Our goal is to find an effective alternative to reward shaping, without using costly human demonstrations, that would also be applicable to a wide range of domains. Hence, we propose to use model predictive control~(MPC) as an experience source for training RL agents in sparse reward environments. Without the need for reward shaping, we successfully apply our approach in the field of mobile robot navigation both in simulation and real-world experiments with a Kuboki Turtlebot 2. We furthermore demonstrate great improvement over pure RL algorithms in terms of success rate as well as number of collisions and timeouts. Our experiments show that MPC as an experience source improves the agent's learning process for a given task in the case of sparse rewards.

A distributed coordination method for solving multi-vehicle lane changes for connected autonomous vehicles (CAVs) is presented. Existing approaches to multi-vehicle lane changes are passive and opportunistic as they are implemented only when the environment allows it. The novel approach of this paper relies on the role of a facilitator assigned to a CAV. The facilitator interacts with and modifies the environment to enable lane changes of other CAVs. Distributed MPC path planners and a distributed coordination algorithm are used to control the facilitator and other CAVs in a proactive and cooperative way. We demonstrate the effectiveness of the proposed approach through numerical simulations. In particular, we show enhanced feasibility of a multi-CAV lane change in comparison to the simultaneous multi-CAV lane change approach in various traffic conditions generated by using a data-set from real-traffic scenarios.

The multi-agent setting is intricate and unpredictable since the behaviors of multiple agents influence one another. To address this environmental uncertainty, distributional reinforcement learning algorithms that incorporate uncertainty via distributional output have been integrated with multi-agent reinforcement learning (MARL) methods, achieving state-of-the-art performance. However, distributional MARL algorithms still rely on the traditional $\epsilon$-greedy, which does not take cooperative strategy into account. In this paper, we present a risk-based exploration that leads to collaboratively optimistic behavior by shifting the sampling region of distribution. Initially, we take expectations from the upper quantiles of state-action values for exploration, which are optimistic actions, and gradually shift the sampling region of quantiles to the full distribution for exploitation. By ensuring that each agent is exposed to the same level of risk, we can force them to take cooperatively optimistic actions. Our method shows remarkable performance in multi-agent settings requiring cooperative exploration based on quantile regression appropriately controlling the level of risk.

In this study, an inhomogeneous Cosserat rod theory is introduced and compared to the conventional homogeneous rod for modeling soft manipulators. The inhomogeneity is addressed by considering the pressure actuation as part of the rod's constitutive laws, resulting in shifting the neutral axis. This shift is investigated for a soft manipulator with three parallel fiber-reinforced actuators. Furthermore, a fiber-reinforced actuator is modeled using nonlinear continuum mechanics to extract the effect of radial pressure on axial deformation and is combined with Cosserat model. Finally, several numerical methods are employed to solve the proposed model and validated by a series of experiments.

Reinforcement Learning (RL) is an area of machine learning figuring out how agents take actions in an unknown environment to maximize its rewards. Unlike classical Markov Decision Process (MDP) in which agent has full knowledge of its state, rewards, and transitional probability, reinforcement learning utilizes exploration and exploitation for the model uncertainty. Under the condition that the model usually has a large state space, a neural network (NN) can be used to correlate its input state to its output actions to maximize the agent's rewards. However, building and training an efficient neural network is challenging. Inspired by Double Q-learning and Asynchronous Advantage Actor-Critic (A3C) algorithm, we will propose and implement an improved version of Double A3C algorithm which utilizing the strength of both algorithms to play OpenAI Gym Atari 2600 games to beat its benchmarks for our project.

Altitude-controlled balloons hold great promise for performing high-priority scientific investigations of Venus's atmosphere and geological phenomena, including tectonic and volcanic activity, as demonstrated by a number of recent Earth-based experiments. In this paper, we explore a concept of operations where multiple autonomous, altitude-controlled balloons monitor explosive volcanic activity on Venus through infrasound microbarometers, and autonomously navigate the uncertain wind field to perform follow-on observations of detected events of interest. We propose a novel autonomous guidance technique for altitude-controlled balloons in Venus's uncertain wind field, and show the approach can result in an increase of up to 63% in the number of close-up observations of volcanic events compared to passive drifters, and a 16% increase compared to ground-in-the-loop guidance. The results are robust to uncertainty in the wind field, and hold across large changes in the frequency of explosive volcanic events, sensitivity of the microbarometer detectors, and numbers of aerial platforms.

Several theoretical works have shown that solitons -- waves that self-maintain constant shape and velocity as they propagate -- can be used as a physical computational reservoir, a concept where machine learning algorithms designed for digital computers are replaced by analog physical systems that exhibit nonlinear dynamical behaviour. Here we propose and experimentally validate a novel reservoir computing (RC) system that for the first time employs solitary-like (SL) waves propagating on the surface of a liquid film flowing over an inclined surface. We demonstrate the ability of the SL wave RC system (SLRC) to forecast chaotic time series and to successfully pass essential benchmark tests, including a memory capacity test and a Mackey-Glass model test.