Monte Carlo tree search (MCTS) has been successful in a variety of domains, but faces challenges with long-horizon exploration when compared to sampling-based motion planning algorithms like Rapidly-Exploring Random Trees. To address these limitations of MCTS, we derive a tree search algorithm based on policy optimization with state occupancy measure regularization, which we call {\it Volume-MCTS}. We show that count-based exploration and sampling-based motion planning can be derived as approximate solutions to this state occupancy measure regularized objective. We test our method on several robot navigation problems, and find that Volume-MCTS outperforms AlphaZero and displays significantly better long-horizon exploration properties.

Integrating robotics into human-centric environments such as homes, necessitates advanced manipulation skills as robotic devices will need to engage with articulated objects like doors and drawers. Key challenges in robotic manipulation are the unpredictability and diversity of these objects' internal structures, which render models based on priors, both explicit and implicit, inadequate. Their reliability is significantly diminished by pre-interaction ambiguities, imperfect structural parameters, encounters with unknown objects, and unforeseen disturbances. Here, we present a prior-free strategy, Tac-Man, focusing on maintaining stable robot-object contact during manipulation. Utilizing tactile feedback, but independent of object priors, Tac-Man enables robots to proficiently handle a variety of articulated objects, including those with complex joints, even when influenced by unexpected disturbances. Demonstrated in both real-world experiments and extensive simulations, it consistently achieves near-perfect success in dynamic and varied settings, outperforming existing methods. Our results indicate that tactile sensing alone suffices for managing diverse articulated objects, offering greater robustness and generalization than prior-based approaches. This underscores the importance of detailed contact modeling in complex manipulation tasks, especially with articulated objects. Advancements in tactile sensors significantly expand the scope of robotic applications in human-centric environments, particularly where accurate models are difficult to obtain.

GEO communication satellites generate significant revenue but can only function reliably for approximately 10 years on orbit. One of the main drivers that limits the reliability of a GEO satellite is the electric power system, and in particular, anomalies related to batteries and degradation of the solar arrays. Given the high cost and relatively short lifespan of GEO satellites, there has been increased research activity towards developing on-orbit servicing systems. However, most of the existing servicing systems are expensive, highly customized, and focus on refueling tasks. On-orbit refueling can be very useful, however, it does not improve satellite reliability which is crucial for long-term missions. Therefore, we propose SSPARE (Space Solar Power Autonomously Reconfigurable Elements), a cost-effective, self-servicing power system. Aside from improving satellite reliability, SSPARE enables to generate up to 6 times more power per launch compared to a traditional GEO communication satellite. This study explores why GEO satellites fail and elaborates on the SSPARE concept. A comparison of SSPARE against a traditional on-orbit servicing mission highlights the benefits of the proposed concept. With humanity striving to become more and more Earth-independent, this work aims to build a foundation for future systems such as large solar power farms on-orbit.

We demonstrate the effectiveness of simple observer-based linear feedback policies for "pixels-to-torques" control of robotic systems using only a robot-facing camera. Specifically, we show that the matrices of an image-based Luenberger observer (linear state estimator) for a "student" output-feedback policy can be learned from demonstration data provided by a "teacher" state-feedback policy via simple linear-least-squares regression. The resulting linear output-feedback controller maps directly from high-dimensional raw images to torques while being amenable to the rich set of analytical tools from linear systems theory, allowing us to enforce closed-loop stability constraints in the learning problem. We also investigate a nonlinear extension of the method via the Koopman embedding. Finally, we demonstrate the surprising effectiveness of linear pixels-to-torques policies on a cartpole system, both in simulation and on real-world hardware. The policy successfully executes both stabilizing and swing-up trajectory tracking tasks using only camera feedback while subject to model mismatch, process and sensor noise, perturbations, and occlusions.

Understanding structure-property relationships of Li-ion battery cathodes is crucial for optimizing rate-performance and cycle-life resilience. However, correlating the morphology of cathode particles, such as in NMC811, and their inner grain architecture with electrode performance is challenging, particularly, due to the significant length-scale difference between grain and particle sizes. Experimentally, it is currently not feasible to image such a high number of particles with full granular detail to achieve representivity. A second challenge is that sufficiently high-resolution 3D imaging techniques remain expensive and are sparsely available at research institutions. To address these challenges, a stereological generative adversarial network (GAN)-based model fitting approach is presented that can generate representative 3D information from 2D data, enabling characterization of materials in 3D using cost-effective 2D data. Once calibrated, this multi-scale model is able to rapidly generate virtual cathode particles that are statistically similar to experimental data, and thus is suitable for virtual characterization and materials testing through numerical simulations. A large dataset of simulated particles with inner grain architecture has been made publicly available.

We discuss a connection between a generative model, called the diffusion model, and nonequilibrium thermodynamics for the Fokker-Planck equation, called stochastic thermodynamics. Based on the techniques of stochastic thermodynamics, we derive the speed-accuracy trade-off for the diffusion models, which is a trade-off relationship between the speed and accuracy of data generation in diffusion models. Our result implies that the entropy production rate in the forward process affects the errors in data generation. From a stochastic thermodynamic perspective, our results provide quantitative insight into how best to generate data in diffusion models. The optimal learning protocol is introduced by the conservative force in stochastic thermodynamics and the geodesic of space by the 2-Wasserstein distance in optimal transport theory. We numerically illustrate the validity of the speed-accuracy trade-off for the diffusion models with different noise schedules such as the cosine schedule, the conditional optimal transport, and the optimal transport.

A tech expert with a track record of predicting sea changes in the industry has made several eye-popping new forecasts in a new book. Google's Ray Kurzweil famously predicted the iPhone era and the fact that a computer would beat someone at chess by 1998. In his new book, 'The Singularity is Nearer', Kurzweil predicts that humans fully merge with AI, becoming immortal cyborgs, by 2045. He also predicts that advancements in AI will make it possible to resurrect loved ones and connect our brains to cloud technology, in what he calls the'fifth epoch' of human intelligence. Google's Ray Kurzweil believes immortality is around the corner (Getty) The singularity is the idea that artificial intelligence (AI) will eventually surpass human intelligence, fundamentally changing human existence.

When Google announced this week that its climate emissions had risen by 48% since 2019, it pointed the finger at artificial intelligence. U.S. tech firms are building vast networks of data centers across the globe and say AI is fueling the growth, throwing the spotlight on the amount of energy the technology is sucking up and its impact on the environment. How does AI use electricity?

Executing flow estimation using Deep Learning (DL)-based soft sensors on resource-limited IoT devices has demonstrated promise in terms of reliability and energy efficiency. However, its application in the field of wastewater flow estimation remains underexplored due to: (1) a lack of available datasets, (2) inconvenient toolchains for on-device AI model development and deployment, and (3) hardware platforms designed for general DL purposes rather than being optimized for energy-efficient soft sensor applications. This study addresses these gaps by proposing an automated, end-to-end solution for wastewater flow estimation using a prototype IoT device.

Recent interest in humanoid robots as general purpose robots has lead to a significant increase in humanoid robotics research and development in both industry and academia. A main reason for the interest is because humanoid robots have the ability to perform repetitive and dull tasks in human environments. A core skill necessary for many tasks, like moving boxes around a warehouse, is robust locomotion. Locomotion planning and control algorithms vary greatly from linear inverted pendulum walking (LIPM) [4] to online whole-body MPC walking [3]. Reinforcement learning (RL) has also been a method of choice recently for robotic motion generation given its ability to adapt to different environments or conditions and generalize well to many scenarios.