Robots interacting with humans must not only generate learned movements in real-time, but also infer the intent behind observed behaviors and estimate the confidence of their own inferences. This paper proposes a unified model that achieves all three capabilities within a single hierarchical predictive-coding recurrent neural network (PC-RNN) equipped with a class embedding vector, CERNet, which leverages a dynamically updated class embedding vector to unify motor generation and recognition. The model operates in two modes: generation and inference. In the generation mode, the class embedding constrains the hidden state dynamics to a class-specific subspace; in the inference mode, it is optimized online to minimize prediction error, enabling real-time recognition. Validated on a humanoid robot across 26 kinesthetically taught alphabets, our hierarchical model achieves 76% lower trajectory reproduction error than a parameter-matched single-layer baseline, maintains motion fidelity under external perturbations, and infers the demonstrated trajectory class online with 68% Top-1 and 81% Top-2 accuracy. Furthermore, internal prediction errors naturally reflect the model's confidence in its recognition. This integration of robust generation, real-time recognition, and intrinsic uncertainty estimation within a compact PC-RNN framework offers a compact and extensible approach to motor memory in physical robots, with potential applications in intent-sensitive human-robot collaboration.

Note: This manuscript has been accepted for publication at a conference in 2024 and will be published under the same title. The version in this pre-print will undergo minor edits and thus does not represent the final version of this work. Abstract-- Owing to the recent success of Large Language Models, Modern A.I has been much focused on linguistic interactions with humans but less focused on nonlinguistic forms of communication between man and machine. In the present paper, we test how affective-linguistic communication, in combination with differential outcomes training, affects mutual learning in a human-robot context. Taking inspiration from child-caregiver dynamics, our human-robot interaction setup consists of a (simulated) robot attempting to learn how best to communicate internal, homeostatically-controlled needs; while a human "caregiver" attempts to learn the correct object to satisfy the robot's present communicated need. We studied the effects of i) human training type, and ii) robot reinforcement learning type, to assess mutual learning terminal accuracy and rate of learning (as measured by the average reward achieved by the robot). Our results find mutual learning between a human and a robot is significantly improved with Differential Outcomes Training (DOT) compared to Non-DOT (control) conditions. We find further improvements when the robot uses an exploration-exploitation policy selection, compared to purely exploitation policy selection. These findings have implications for utilizing socially assistive robots (SAR) in therapeutic contexts, e.g. for cognitive interventions, and educational applications.

We spoke to the exhibitors to get real-life demos of their products. Tangram Vision is a hardware-agnostic sensor fusion platform. Their co-founder, Adam Rodnitzky, walks us through their sensor fusion platform. Matt Bilsky, Founder and CEO of FLX Solutions gives us a live demo of their robot, the FLX BOT. Matt Bilsky applied his Ph.D. in Mechanical Engineering to create a novel, highly compact robot that is designed to reach and inspect parts of a building that a human cannot reach.

Last year at CES French startup Pollen Robotics debuted Reachy, an open-source humanoid robot (the top half of one at least) capable of performing a wide variety of tasks -- from traditional R&D to product demonstrations and food service. This year, Reachy is back and more capable than ever before. Rather than program in Reachy's movements, users can now control the robot directly simply by donning a VR headset. Once paired to Reachy, the user can see what the robot sees through its front cameras and control the robot's arms via VR controllers to, say, play a game of tic-tac-toe on the CES show floor. This method can also be used to quickly train Reachy for delicate tasks requiring fine motor control, rather than programming those movements manually. The company has also reportedly upgraded Reachy's cameras and processor since last year, though Reachy will still set you back around $17,000.

Seems like everybody's getting into the AI and robotics game -- at least the companies and research institutions that can afford to build their platforms from the ground up are. France's Pollen Robotics, on the other hand, aims to kickstart the robotics revolution with its open-source system, Reachy. The robot, being open-source, is capable of so much more. Developers can use Python to create myriad applications for the system, while the robot's modular nature allows for any number of applications whether that's food service, customer service, demonstrations or good old fashioned research and development. The system comes with built-in AI which should help developers jump straight into the meat of their research without first having to train up the machine learning component.