Reinforcement Learning (RL) of contact-rich manipulation tasks has yielded impressive results in recent years. While many studies in RL focus on varying the observation space or reward model, few efforts focused on the choice of action space (e.g. joint or end-effector space, position, velocity, etc.). However, studies in robot motion control indicate that choosing an action space that conforms to the characteristics of the task can simplify exploration and improve robustness to disturbances. This paper studies the effect of different action spaces in deep RL and advocates for Variable Impedance Control in End-effector Space (VICES) as an advantageous action space for constrained and contact-rich tasks. We evaluate multiple action spaces on three prototypical manipulation tasks: Path Following (task with no contact), Door Opening (task with kinematic constraints), and Surface Wiping (task with continuous contact). We show that VICES improves sample efficiency, maintains low energy consumption, and ensures safety across all three experimental setups. Further, RL policies learned with VICES can transfer across different robot models in simulation, and from simulation to real for the same robot. Further information is available at https://stanfordvl.github.io/vices.

FREMONT, CA – Industries and organizations across the globe have realized the potential of artificial intelligence (AI), and the oil and gas industry is one of them. Petroleum oil is one of the most prominent resources in the energy sector and is the basis for many products such as wax, lubricant, kerosene, petroleum jelly, and so on. Over the last few years, the crude oil reserves are steadily reaching their limits. Also, the rise of alternative fuel sources has resulted in the reduction of oil prices, which has raised concerns in the oil and gas sector. To alleviate the adverse effects plaguing the industry, many organizations are turning toward modern technologies to increase productivity as well as revenue.

SOME PEOPLE fear about robots taking work far from human beings, however there are a pair of jobs that even these sceptics admit most folk would no longer favor. One is cleansing up radioactive slay, in particular when it's miles internal a nuclear vitality self-discipline--and in particular if the vitality self-discipline in quiz has suffered a recent accident. These that gain contend with radioactive arena topic must first don protective suits that are inherently cumbersome and are additional encumbered by the air hoses wanted to allow the wearer to breathe. Even then their working hours are strictly restricted, in relate to resolve far from prolonged exposure to radiation and because operating in the suits is intelligent. Moreover, some forms of slay are too dangerous for even the besuited to intention safely.

SOME PEOPLE fear about robots taking work far from human beings, however there are a pair of jobs that even these sceptics admit most folk would no longer favor. One is cleansing up radioactive slay, in particular when it's miles internal a nuclear vitality self-discipline--and in particular if the vitality self-discipline in quiz has suffered a recent accident. These that gain contend with radioactive arena topic must first don protective suits that are inherently cumbersome and are additional encumbered by the air hoses wanted to allow the wearer to breathe. Even then their working hours are strictly restricted, in relate to resolve far from prolonged exposure to radiation and because operating in the suits is intelligent. Moreover, some forms of slay are too dangerous for even the besuited to intention safely.

Lots of experimental robots involve a little bit of cheating. Rather than containing all the necessary electronics and energy sources, they have tethers and wires that provide power and control without weighing the robot down or taking up too much internal space. This is especially true for soft-bodied robots, which typically pump air or fluids to drive their motion. Having to incorporate a power source, pumps, and a reservoir of gas or liquid would significantly increase the weight and complexity of the robot. A team from Cornell University has now demonstrated a clever twist that cuts down on the weight and density of all of this by figuring out how to get one of the materials to perform two functions.

Lots of experimental robots involve a little bit of cheating. Rather than containing all the necessary electronics and energy sources, they have tethers and wires that provide power and control without weighing the robot down or taking up too much internal space. This is especially true for soft-bodied robots, which typically pump air or fluids to drive their motion. Having to incorporate a power source, pumps, and a reservoir of gas or liquid would significantly increase the weight and complexity of the robot. A team from Cornell University has now demonstrated a clever twist that cuts down on the weight and density of all of this by figuring out how to get one of the materials to perform two functions.

Damage due to earthquakes poses a threat to humans worldwide. To estimate the hazard, scientists use historical earthquake data and ground motion recorded by seismometers at different locations. However, the current approaches are mostly empirical and may not capture the full range of ground shaking in future large earthquakes due to a lack of historical geological data. This leads to significant uncertainties in hazard estimates. Not only that, due to the lack of sufficient historical data, scientists mostly rely on simulated data, which is computationally expensive.

AI (Artificial Intelligence) is everywhere and it's here to stay. Along with these consumer applications, companies across sectors are increasingly harnessing AI's power for productivity growth and innovation. There are many who believe that AI has the potential to become more significant than even the internet. Availability of enormous amount of data combined with huge leap in computational power and huge improvements in engineering skills should help AI, backed with deep learning, to make huge impact across various facets of human life. Amid all the hype, genuine and inflated, around the world of AI, it is pertinent to ask an important question.

Traditionally, supercomputer performance is measured using the High-Performance Linpack (HPL) benchmark, which is the basis for the Top500 list that biannually ranks world's fastest supercomputers. The Linpack benchmark tests a supercomputer's ability to conduct high-performance tasks (like simulations) that use double-precision math. On June's Top500 list, announced Monday, Summit's 148 Linpack petaflops land it first place by a comfortable margin. Using that same machine configuration, Oak Ridge National Laboratory (ORNL) and Nvidia have tested Summit on HPL-AI and gotten a result of 445 petaflops. While the HPL benchmark tests supercomputers' performance in double-precision math, AI is a rapidly growing use case for supercomputers -- and most AI models use mixed-precision math.

Artificial intelligence can already help make medical diagnoses and weed out terrorists. Now Microsoft wants AI to make our planet greener. Ranked the No. 1 environmentally friendly company by the nonprofit Just Capital, the tech giant is finding innovative ways to combat climate change. Chief among them: a grant launched in 2017 that funds the use of AI to address global warming. The tech company also released code that can aid developers building such algorithms.