Reinforcement Learning (RL) has witnessed great strides for quadruped locomotion, with continued progress in the reliable sim-to-real transfer of policies. However, it remains a challenge to reuse a policy on another robot, which could save time for retraining. In this work, we present a framework for zero-shot policy retargeting wherein diverse motor skills can be transferred between robots of different shapes and sizes. The new framework centers on a planning-and-control pipeline that systematically integrates RL and Model Predictive Control (MPC). The planning stage employs RL to generate a dynamically plausible trajectory as well as the contact schedule, avoiding the combinatorial complexity of contact sequence optimization. This information is then used to seed the MPC to stabilize and robustify the policy roll-out via a new Hybrid Kinodynamic (HKD) model that implicitly optimizes the foothold locations. Hardware results show an ability to transfer policies from both the A1 and Laikago robots to the MIT Mini Cheetah robot without requiring any policy re-tuning.

Reinforcement Learning (RL) techniques have drawn great attention in many challenging tasks, but their performance deteriorates dramatically when applied to real-world problems. Various methods, such as domain randomization, have been proposed to deal with such situations by training agents under different environmental setups, and therefore they can be generalized to different environments during deployment. However, they usually do not incorporate the underlying environmental factor information that the agents interact with properly and thus can be overly conservative when facing changes in the surroundings. In this paper, we first formalize the task of adapting to changing environmental dynamics in RL as a generalization problem using Contextual Markov Decision Processes (CMDPs). We then propose the Asymmetric Actor-Critic in Contextual RL (AACC) as an end-to-end actor-critic method to deal with such generalization tasks. We demonstrate the essential improvements in the performance of AACC over existing baselines experimentally in a range of simulated environments.

Cutting-edge robots are on display at the 2019 World Robot Conference in Beijing, running from August 20 to 25, are expected to attract nearly 200 guests from 22 countries. The conference features a series of exhibition areas for new robotic technologies and products - including medical, multi-legged, and smart logistics - as well as four contests with an anticipated 4,500 professional participants. Over 700 robots specialising with more than 21 industrial applications will be exhibited between now and the close of the conference. Among those exhibiting will be HRG Robotics, whose, president Wang Meng, said: 'We will be showcasing a string of successful companies which have got off the ground through the help of HRG, alongside our representative products at WRC 2019, as we aim to form new partnerships with companies around the world.' Also on display will be SmartBird, created by German firm Festo, whose design was inspired by the herring gull and whose flight mimics that of the bird. The ultralight flying drone was created with the best aerodynamics and maximum agility in mind and it is able to take off, fly and land under its own power.

Shortly after SoftBank acquired his company last October, Marc Raibert of Boston Dynamics confessed, "I happen to believe that robotics will be bigger than the Internet." Many sociologists regard the Internet as the single biggest societal invention since the dawn of the printing press in 1440. To fully understand Raibert's point of view, one needs to analyze his zoo of robots which are best know for their awe-striking gait, balance and agility. The newest creation to walk out of Boston Dynamic's lab is SpotMini, the latest evolution of mechanical canines. Big Dog, Spot's unnerving ancestor, first came to public view in 2009 and has racked up quite a YouTube following with more than six and one half million views.

A four-legged, canine-like robot has been introduced to the mass market by a robotics company in China. Unitree Robotics said the initial price for their scary-looking'Laikago' would be around $25,000 (£18,900), but it's set to drop in the future. Previously, US-based Boston Dynamics had developed two dog-like robots, called'Big Dog' and'Spot', but this is the first time such technology has been made available to the general public, according to the creator of'Laikago'. Meet'Laikago': Chinese firm Unitree Robotics has unveiled a four-legged machine (pictured) Unitree Robotics' 'Laikago' has been compared to Cujo, also known as'Big Dog', developed by US-based Boston Dynamics. 'Big Dog' (pictured) took £1.6 million and four years to create Boston Dynamics has also released'Spot', a complex machine that can walk and trot on four legs like a dog.

Of all the legged robots built in labs all over the world, few inspire more awe and reverence than Boston Dynamics' quadrupeds. Chinese roboticist Xing Wang has long been a fan of BigDog, AlphaDog, Spot, SpotMini, and other robots that Boston Dynamics has famously introduced over the years. "Marc Raibert … is my idol," Wang once told us about the founder and president of Boston Dynamics. Now Wang, with funding from a Chinese angel investor, has founded his own robotics company, called Unitree Robotics and based in Hangzhou, outside Shanghai. Wang says his plan is making legged robots as popular and affordable as smartphones and drones. Unitree's first robot is a four-legged robodog called Laikago, which the company is announcing this week.