Human-AI shared control allows human to interact and collaborate with autonomous agents to accomplish control tasks in complex environments.

Despite a slow neuromuscular system, humans easily outperform modern robot technology, especially in physical contact tasks. How is this possible? Biological evidence indicates that motor control of biological systems is achieved by a modular organization of motor primitives, which are fundamental building blocks of motor behavior. Inspired by neuro-motor control research, the idea of using simpler building blocks has been successfully used in robotics. Nevertheless, a comprehensive formulation of modularity for robot control remains to be established. In this paper, we introduce a modular framework for robot control using motor primitives. We present two essential requirements to achieve modular robot control: independence of modules and closure of stability. We describe key control modules and demonstrate that a wide range of complex robotic behaviors can be generated from this small set of modules and their combinations. The presented modular control framework demonstrates several beneficial properties for robot control, including task-space control without solving Inverse Kinematics, addressing the problems of kinematic singularity and kinematic redundancy, and preserving passivity for contact and physical interactions. Further advantages include exploiting kinematic singularity to maintain high external load with low torque compensation, as well as controlling the robot beyond its end-effector, extending even to external objects. Both simulation and actual robot experiments are presented to validate the effectiveness of our modular framework. We conclude that modularity may be an effective constructive framework for achieving robotic behaviors comparable to human-level performance.

Processes of evidence accumulation for motor control contribute to the ecological validity of driver models. According to established theories of cognition, drivers make control adjustments when a process of accumulation of perceptual inputs reaches a decision boundary. Unfortunately, there is not a standard way for building such models, limiting their use. Current implementations are hand-crafted, lack adaptability, and rely on inefficient optimization techniques that do not scale well with large datasets. This paper introduces Akkumula, an evidence accumulation modelling framework built using deep learning techniques to leverage established coding libraries, gradient optimization, and large batch training. The core of the library is based on Spiking Neural Networks, whose operation mimic the evidence accumulation process in the biological brain. The model was tested on data collected during a test-track experiment. Results are promising. The model fits well the time course of vehicle control (brake, accelerate, steering) based on vehicle sensor data. The perceptual inputs are extracted by a dedicated neural network, increasing the context-awareness of the model in dynamic scenarios. Akkumula integrates with existing machine learning architectures, benefits from continuous advancements in deep learning, efficiently processes large datasets, adapts to diverse driving scenarios, and maintains a degree of transparency in its core mechanisms.

In neuroscience and biomedical engineering, accurately modeling the complex movements of the human hand has long been a significant challenge. Current models often struggle to capture the intricate interplay between the brain's motor commands and the physical actions of muscles and tendons. This gap not only hinders scientific progress but also limits the development of effective neuroprosthetics aimed at restoring hand function for those with limb loss or paralysis. EPFL professor Alexander Mathis and his team have developed an AI-driven approach that advances our understanding of these complex motor functions. The team used a creative machine learning strategy that combined curriculum-based reinforcement learning with detailed biomechanical simulations.

Self-supervised skill learning aims to acquire useful behaviors that leverage the underlying dynamics of the environment. Latent variable models, based on mutual information maximization, have been particularly successful in this task but still struggle in the context of robotic manipulation. As it requires impacting a possibly large set of degrees of freedom composing the environment, mutual information maximization fails alone in producing useful manipulation behaviors. To address this limitation, we introduce SLIM, a multi-critic learning approach for skill discovery with a particular focus on robotic manipulation. Our main insight is that utilizing multiple critics in an actor-critic framework to gracefully combine multiple reward functions leads to a significant improvement in latent-variable skill discovery for robotic manipulation while overcoming possible interference occurring among rewards which hinders convergence to useful skills. Furthermore, in the context of tabletop manipulation, we demonstrate the applicability of our novel skill discovery approach to acquire safe and efficient motor primitives in a hierarchical reinforcement learning fashion and leverage them through planning, surpassing the state-of-the-art approaches for skill discovery by a large margin.

Many motor skills in humanoid robotics can be learned using parametrized motor primitives as done in imitation learning. However, most interesting motor learning problems are high-dimensional reinforcement learning problems often beyond the reach of current methods. In this paper, we extend previous work on policy learning from the immediate reward case to episodic reinforcement learning. We show that this results into a general, common framework also connected to policy gradient methods and yielding a novel algorithm for policy learning by assuming a form of exploration that is particularly well-suited for dynamic motor primitives. The resulting algorithm is an EM-inspired algorithm applicable in complex motor learning tasks.

Human-AI shared control allows human to interact and collaborate with autonomous agents to accomplish control tasks in complex environments. Previous Reinforcement Learning (RL) methods attempted goal-conditioned designs to achieve human-controllable policies at the cost of redesigning the reward function and training paradigm. Inspired by the neuroscience approach to investigate the motor cortex in primates, we develop a simple yet effective frequency-based approach called Policy Dissection to align the intermediate representation of the learned neural controller with the kinematic attributes of the agent behavior. Without modifying the neural controller or retraining the model, the proposed approach can convert a given RL-trained policy into a human-controllable policy. We evaluate the proposed approach on many RL tasks such as autonomous driving and locomotion. The experiments show that human-AI shared control system achieved by Policy Dissection in driving task can substantially improve the performance and safety in unseen traffic scenes. With human in the inference loop, the locomotion robots also exhibit versatile controllable motion skills even though they are only trained to move forward. Our results suggest the promising direction of implementing human-AI shared autonomy through interpreting the learned representation of the autonomous agents. Code and demo videos are available at https://metadriverse.github.io/policydissect.

Inspired by the unique neurophysiology of the octopus, we propose a hierarchical framework that simplifies the coordination of multiple soft arms by decomposing control into high-level decision making, low-level motor activation, and local reflexive behaviors via sensory feedback. When evaluated in the illustrative problem of a model octopus foraging for food, this hierarchical decomposition results in significant improvements relative to end-to-end methods. Performance is achieved through a mixed-modes approach, whereby qualitatively different tasks are addressed via complementary control schemes. Here, model-free reinforcement learning is employed for high-level decision-making, while model-based energy shaping takes care of arm-level motor execution. To render the pairing computationally tenable, a novel neural-network energy shaping (NN-ES) controller is developed, achieving accurate motions with time-to-solutions 200 times faster than previous attempts. Our hierarchical framework is then successfully deployed in increasingly challenging foraging scenarios, including an arena littered with obstacles in 3D space, demonstrating the viability of our approach.