Humans excel in analogical learning and knowledge transfer and, more importantly, possess a unique understanding of identifying appropriate sources of knowledge. From a model's perspective, this presents an interesting challenge. If models could autonomously retrieve knowledge useful for transfer or decision-making to solve problems, they would transition from passively acquiring to actively accessing and learning from knowledge. However, filling models with knowledge is relatively straightforward -- it simply requires more training and accessible knowledge bases. The more complex task is teaching models about which knowledge can be analogized and transferred. Therefore, we design a knowledge augmentation method LEKA for knowledge transfer that actively searches for suitable knowledge sources that can enrich the target domain's knowledge. This LEKA method extracts key information from textual information from the target domain, retrieves pertinent data from external data libraries, and harmonizes retrieved data with the target domain data in feature space and marginal probability measures. We validate the effectiveness of our approach through extensive experiments across various domains and demonstrate significant improvements over traditional methods in reducing computational costs, automating data alignment, and optimizing transfer learning outcomes.

Nearly three years ago, Leka won the Grand Prize at the 2014 Robot Launch competition for their robotic toy set on changing the way children with developmental disorders learn, play and progress. Leka will be the first interactive tool for children with developmental disorders that is available for direct purchase to the public. Designed for use in the home and not limited to a therapist's office, Leka enables streamlined communication between therapists, parents and children easier, more efficient and more accessible through its monitoring platform. Leka's co-founder and CEO, Ladislas de Toldi, writes about Leka's progress since the Robot Launch competition and where the company is headed in the next year. Since winning the Robot Launch competition in 2014, Leka has made immense progress and is well on it's way to getting in the hands of exceptional children around the globe.

We expected to see artificial intelligence (AI), home and vehicle automation, smarter devices, augmented and virtual reality, and IoT to dominate at CES 2017. And truth be told it most certainly is not failing to deliver. In addition to new products in the usual consumer device categories like video game tech, TVs, and audio equipment we're seeing loads of the new trending technologies being showcased and it's clear that Christmas is not over at CES 2017. Everything from smart home bots, hacker-fighting routers and wallpaper TVs to super cool Lego Boost robotic kits that teach kids to code, is being shown off at the popular tech event making it super difficult to choose the coolest of them all. That said, here's a look at some of the top AI enabled tech and gadgets at CES 2017.

The rolling robot BB-8 captivated moviegoers as it helped save the day in the 2016 film "Star Wars: The Force Awakens" -- though even the most die-hard fan would admit that we aren't likely to see a real-world robot quite like that in the near future. However, there's another spherical, programmable, rolling robot currently in development that's capable of doing important work to engage children with special needs, particularly children on the autism spectrum. Described by its designers as "a robotic companion," the roly-poly Leka robot is shaped like a ball, has an endearing "face" that changes expressions, and uses sound, light and colors to interact with users through customizable games that improve cognitive and motor skills. Caregivers and educators can program the toy to guide children with developmental disabilities through a range of activities, helping them to improve communication and learn to connect with their environment and with others around them. For children with Autism Spectrum Disorder (ASD), connecting with others and interpreting social cues can be enormously challenging.

Video Friday is your weekly selection of awesome robotics videos, collected by your slow-running Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next two months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. Snake Monster (a hexapod built with snake robot parts) has gotten even more monstrous. A demonstration of mobile manipulation with "Snake Monster," a hexapod robot built with modular actuators in the Biorobotics Lab, at the Robotics Institute of Carnegie Mellon University.