Rami Sinno is crouched beside a filing cabinet, wrestling a beach-ball sized disc out of a box, when a dull thump echoes around his laboratory. "I just dropped tens of thousands of dollars' worth of material," he says with a laugh. Straightening up, Sinno reveals the goods: a golden silicon wafer, which glitters in the fluorescent light of the lab. This circular platter is divided into some 100 rectangular tiles, each of which contains billions of microscopic electrical switches. These are the brains of Amazon's most advanced chip yet: the Trainium 2, announced in December.

Haptic feedback is essential for dexterous telemanipulation that enables operators to control robotic hands remotely with high skill and precision, mimicking a human hand's natural movement and sensation. However, current haptic methods for dexterous telemanipulation cannot support torque feedback, resulting in object rotation and rolling mismatches. The operator must make tedious adjustments in these tasks, leading to delays, reduced situational awareness, and suboptimal task performance. This work presents a Bi-directional Momentum-based Haptic Feedback and Control (Bi-Hap) system for real-time dexterous telemanipulation. Bi-Hap integrates multi-modal sensors to extract human interactive information with the object and share it with the robot's learning-based controller. A Field-Oriented Control (FOC) algorithm is developed to enable the integrated brushless active momentum wheel to generate precise torque and vibrative feedback, bridging the gap between human intent and robotic actions. Different feedback strategies are designed for varying error states to align with the operator's intuition. Extensive experiments with human subjects using a virtual Shadow Dexterous Hand demonstrate the effectiveness of Bi-Hap in enhancing task performance and user confidence. Bi-Hap achieved real-time feedback capability with low command following latency (delay<0.025s) and highly accurate torque feedback (RMSE<0.010 Nm).

Abstract-- Complex multibody legged robots can have complex rotational control challenges. In this paper, we propose a concise way to understand and formulate a whole-body orientation that (i) depends on system configuration only and not a history of motion, (ii) can be representative of the orientation of the entire system while not being attached to any specific link, and (iii) has a rate of change that approximates total system angular momentum. We relate this orientation coordinate to past work, and discuss and demonstrate, including on hardware, several different uses for it. Many legged robots are best represented by nontrivial multibody dynamic models. The total system center of mass (CoM) is likely the most well-known of these model-based coordinates.

This post is a commentary on the MLCommons article "Perspective: Unlocking ML requires an ecosystem approach" by Peter Mattson, Aarush Selvan, David Kanter, Vijay Janapa Reddi, Roger Roberts, and Jacomo Corbo. The world of artificial intelligence (AI) and machine learning (ML) is undergoing a sea change from science to engineering at scale. Over the past decade, the volume of AI research has skyrocketed as the cost to train and deploy commercial models has decreased. Between 2015 and 2021, the cost to train an image classification system fell by 64 percent, while training times improved by 94 percent in the same period.1 The emergence of foundation models--large-scale, deep learning models trained on massive, broad, unstructured data sets--has enabled entrepreneurs and business executives to see the possibility of true scale.

Generative AI is an artificial intelligence model that, when trained on massive datasets, can generate text, images, audio, and video by predicting the next word or pixel. The simplest input (called a prompt) to generative AI is a text description. Based on that text description, a generative pre-trained transformer (GPT) can write a paragraph, a text-to-image model such as Stable Diffusion can create a picture, MusicLM can create music, and Imagen Video can create a video. This technology will democratize all kinds of content creation. For video creation it could level the playing field more than smartphones and social video platforms have already done.

For legged robots, aerial motions are the only option to overpass obstacles that cannot be circumvent with standard locomotion gaits. In these cases, the robot must perform a leap to either jump onto the obstacle or fly over it. However, these movements represent a challenge because during the flight phase the Center of Mass (CoM) cannot be controlled, and the robot orientation has limited controllability. This paper focuses on the latter issue and proposes an Orientation Control System (OCS) consisting of two rotating and actuated masses (flywheels or reaction wheels) to gain control authority on the robot orientation. Because of the conservation of angular momentum, their rotational velocity can be adjusted to steer the robot orientation even when there are no contacts with the ground. The axes of rotation of the flywheels are designed to be incident, leading to a compact orientation control system that is capable of controlling both roll and pitch angles, considering the different moment of inertia in the two directions. We tested the concept with simulations on the robot Solo12.

Swing arms have an irreplaceable role in promoting highly dynamic locomotion on bipedal robots by a larger angular momentum control space from the viewpoint of biomechanics. Few bipedal robots utilize swing arms and its redundancy characteristic of multiple degrees of freedom due to the lack of appropriate locomotion control strategies to perfectly integrate modeling and control. This paper presents a kind of control strategy by modeling the bipedal robot as a flywheel-spring loaded inverted pendulum (F-SLIP) to extract characteristics of swing arms and using the whole-body controller (WBC) to achieve these characteristics, and also proposes a evaluation system including three aspects of agility defined by us, stability and energy consumption for the highly dynamic locomotion of bipedal robots. We design several sets of simulation experiments and analyze the effects of swing arms according to the evaluation system during the jumping motion of Purple (Purple energy rises in the east)V1.0, a kind of bipedal robot designed to test high explosive locomotion. Results show that Purple's agility is increased by more than 10 percent, stabilization time is reduced by a factor of two, and energy consumption is reduced by more than 20 percent after introducing swing arms.

The current series of articles on MLOps started with an analogy with DevOps. To explain how software updates happen, I am introducing the Known Unknown matrix. The so-called "known unknown" matrix is popularized by Donald Rumsfeld and divides our knowledge into four quadrants: Applied to software development, let us consider what the knowns and the unknowns for the feature team would be. As an example, let us assume that the software is an OCR program that recognizes car license plate numbers based on heuristic algorithms. In Software 1.0 (the traditional software), bugs and feature requests are two cases when software updates are needed.

The term time-series analysis (TSA) refers to the statistical approach to time-series or the analysis of trend and seasonality. It is often an ad hoc exploration and analysis that usually involves visualizing distributions, trends, cyclic patterns, and relationships between features, and between features and the target(s). More generally, we can say TSA is roughly exploratory data analysis (EDA) that's specific to time-series data. This comparison can be misleading however since TSA can include both descriptive and exploratory elements. Let's see quickly the differences between descriptive and exploratory analysis: Therefore, TSA is the initial investigation of a dataset with the goal of discovering patterns, especially trend and seasonality, and obtaining initial insights, testing hypotheses, and extracting meaningful summary statistics.

Strategy Development has followed a set path since the last century where a predetermined, rectilinear, and inflexible approach defined the process. In the 21st century, however, business leaders are devising Strategy by evolving it into a probabilistic, repeated, and multifaceted process. An approach that can both endure and adapt to the growing pace of Change and Disruption that is manifesting itself in all industries. Using gaming, AI, unremitting execution, and adjustment, with numerous scenarios to deliberate on, leaders create "Flywheels" that successfully tackle the not so deterministic world where the future is highly uncertain. Flywheel is a concept originally used in the power industry to explain an origin of stabilization, energy storage, and momentum.