Collaborating Authors

Training Humans to Train Robots Dynamic Motor Skills Artificial Intelligence

Learning from demonstration (LfD) is commonly considered to be a natural and intuitive way to allow novice users to teach motor skills to robots. However, it is important to acknowledge that the effectiveness of LfD is heavily dependent on the quality of teaching, something that may not be assured with novices. It remains an open question as to the most effective way of guiding demonstrators to produce informative demonstrations beyond ad hoc advice for specific teaching tasks. To this end, this paper investigates the use of machine teaching to derive an index for determining the quality of demonstrations and evaluates its use in guiding and training novices to become better teachers. Experiments with a simple learner robot suggest that guidance and training of teachers through the proposed approach can lead to up to 66.5% decrease in error in the learnt skill.

What is machine learning? Everything you need to know Creative teaching and learning


Most likely you have heard the term "transferable skills" before, especially if you have ever had to search for employment. These skills, as defined by the career development website LiveCareer, are those that you have "acquired during any activity in your life – jobs, classes, projects, parenting, hobbies, sports, virtually anything – that are transferable and applicable to what you want to do in your next job" ..."

Machine Learning Vs Machine Teaching: A Whole New Approach To Imparting Human Skills


There is no doubt that machine learning is one of the major driving forces behind most of the advanced techs and gadgets we have today. Whether it is your smart home device or that newly bought self-driving car yours, ML is playing a vital role not only advancing gadgets but is also changing the way people interact with machines. No doubt, it is one of the hottest technologies in the world. However, people almost forget that there is something called Machine Teaching that also plays a significant role in all the ML use cases. We all have heard a lot about ML, which is also seen as a subset of artificial intelligence.

Discovering Generalizable Skills via Automated Generation of Diverse Tasks Artificial Intelligence

The learning efficiency and generalization ability of an intelligent agent can be greatly improved by utilizing a useful set of skills. However, the design of robot skills can often be intractable in real-world applications due to the prohibitive amount of effort and expertise that it requires. In this work, we introduce Skill Learning In Diversified Environments (SLIDE), a method to discover generalizable skills via automated generation of a diverse set of tasks. As opposed to prior work on unsupervised discovery of skills which incentivizes the skills to produce different outcomes in the same environment, our method pairs each skill with a unique task produced by a trainable task generator. To encourage generalizable skills to emerge, our method trains each skill to specialize in the paired task and maximizes the diversity of the generated tasks. A task discriminator defined on the robot behaviors in the generated tasks is jointly trained to estimate the evidence lower bound of the diversity objective. The learned skills can then be composed in a hierarchical reinforcement learning algorithm to solve unseen target tasks. We demonstrate that the proposed method can effectively learn a variety of robot skills in two tabletop manipulation domains. Our results suggest that the learned skills can effectively improve the robot's performance in various unseen target tasks compared to existing reinforcement learning and skill learning methods.

AI Startup Embodied Intelligence Wants Robots to Learn From Humans in Virtual Reality

IEEE Spectrum Robotics

We are building technology that enables existing robot hardware to handle a much wider range of tasks where existing solutions break down, for example, bin picking of complex shapes, kitting, assembly, depalletizing of irregular stacks, and manipulation of deformable objects such as wires, cables, fabrics, linens, fluid-bags, and food. To equip existing robots with these skills, our software builds on the latest advances in deep reinforcement learning, deep imitation learning, and few-shot learning, to all of which the founding team has made significant contributions.