Hamiltonian Monte Carlo (HMC) has emerged as a powerful Markov Chain Monte Carlo (MCMC) method to sample from complex continuous distributions.

PGMax is an open-source Python package for easy specification of discrete Probabilistic Graphical Models (PGMs) as factor graphs, and automatic derivation of efficient and scalable loopy belief propagation (LBP) implementation in JAX. It supports general factor graphs, and can effectively leverage modern accelerators like GPUs for inference. Compared with existing alternatives, PGMax obtains higher-quality inference results with orders-of-magnitude inference speedups. PGMax additionally interacts seamlessly with the rapidly growing JAX ecosystem, opening up exciting new possibilities. Our source code, examples and documentation are available at https://github.com/vicariousinc/PGMax.

Robots are assuming control over the world. Yet, they are turning out to be progressively common in pretty much every industry, from medical to defence and even education. At robotics organizations across the world, the coexisting of designing and science is delivering some genuinely inventive items -- things that do what people have regularly done, just better. Regardless of whether it's welding, educating, collecting vehicles, or doing a medical procedure, these developments are changing the manner in which we live and work. What they do: Anduril is devoted to building cutting-edge and programming items that current answers for the greatest security difficulties of America and its partners.

Life's most valuable asset is health. Continuously understanding the state of our health and modeling how it evolves is essential if we wish to improve it. Given the opportunity that people live with more data about their life today than any other time in history, the challenge rests in interweaving this data with the growing body of knowledge to compute and model the health state of an individual continually. This dissertation presents an approach to build a personal model and dynamically estimate the health state of an individual by fusing multi-modal data and domain knowledge. The system is stitched together from four essential abstraction elements: 1. the events in our life, 2. the layers of our biological systems (from molecular to an organism), 3. the functional utilities that arise from biological underpinnings, and 4. how we interact with these utilities in the reality of daily life. Connecting these four elements via graph network blocks forms the backbone by which we instantiate a digital twin of an individual. Edges and nodes in this graph structure are then regularly updated with learning techniques as data is continuously digested. Experiments demonstrate the use of dense and heterogeneous real-world data from a variety of personal and environmental sensors to monitor individual cardiovascular health state. State estimation and individual modeling is the fundamental basis to depart from disease-oriented approaches to a total health continuum paradigm. Precision in predicting health requires understanding state trajectory. By encasing this estimation within a navigational approach, a systematic guidance framework can plan actions to transition a current state towards a desired one. This work concludes by presenting this framework of combining the health state and personal graph model to perpetually plan and assist us in living life towards our goals.

We introduce a novel formulation for incorporating visual feedback in controlling robots. We define a generative model from actions to image observations of features on the end-effector. Inference in the model allows us to infer the robot state corresponding to target locations of the features. This, in turn, guides motion of the robot and allows for matching the target locations of the features in significantly fewer steps than state-of-the-art visual servoing methods. The training procedure for our model enables effective learning of the kinematics, feature structure, and camera parameters, simultaneously. This can be done with no prior information about the robot, structure, and cameras that observe it. Learning is done sample-efficiently and shows strong generalization to test data. Since our formulation is modular, we can modify components of our setup, like cameras and objects, and relearn them quickly online. Our method can handle noise in the observed state and noise in the controllers that we interact with. We demonstrate the effectiveness of our method by executing grasping and tight-fit insertions on robots with inaccurate controllers.

Solving tasks with sparse rewards is a main challenge in reinforcement learning. While hierarchical controllers are an intuitive approach to this problem, current methods often require manual reward shaping, alternating training phases, or manually defined sub tasks. We introduce modulated policy hierarchies (MPH), that can learn end-to-end to solve tasks from sparse rewards. To achieve this, we study different modulation signals and exploration for hierarchical controllers. Specifically, we find that communicating via bit-vectors is more efficient than selecting one out of multiple skills, as it enables mixing between them. To facilitate exploration, MPH uses its different time scales for temporally extended intrinsic motivation at each level of the hierarchy. We evaluate MPH on the robotics tasks of pushing and sparse block stacking, where it outperforms recent baselines.

While the internet spent the last week virtually paralyzed by the Yanny/Laurel debate, the wheels of industry kept turning. Elon Musk promised rides aboard the upcoming Boring Company system would only cost a buck, MIT built a robotic albatross for oceanic observations and Bosch unveiled its anti-skid maneuvering thrusters for high end motorbikes. Numbers, because how else would you know when it's time to get back out on the road again? Behold, whatever the heck this thing is. Once fully developed, it should help drastically reduce the cost of monitoring the health of our oceans (at least near the surface) while severely increasing the amount of open ocean we can monitor at any given time.

I'm watching someone on the edge of a helicopter as he counts down with his hands. Three, two, one, and we leap. Instead, I fall forward into an iFly indoor skydiving wind tunnel and I start to float. This is all happening at indoor skydiving facility, iFly in Union City, California. This week the company introduced its virtual reality flying experience to 28 of the company's 37 locations. In addition to the usual float-above-a-giant-fan, patrons can now put on a VR helmet for about $20 more than the usual cost of about $70 (prices are determined by region) and experience what it's like to leap out of an aircraft above Hawaii, Dubai, Southern California and the Alps.

Tesla CEO Elon Musk and Facebook CEO Mark Zuckerberg had a little tit-for-tat this week over artificial intelligence. Does it represent an existential threat to humanity, as Musk argues, or does it hold great promise to improve our lives, as Zuckerberg believes? On a Facebook Live broadcast, Zuckerberg declared, "I think people who are naysayers and try to drum up these doomsday scenarios -- I just, I don't understand it. It's really negative, and in some ways I actually think it is pretty irresponsible." Musk took the kerfuffle to Twitter, replying: "I've talked to Mark about this. His understanding of the subject is limited."