Shared autonomy in assistive mobile robots: a review

A comprehensive study on Mecanum wheel-based mobility and suspension solutions for intelligent nursing wheelchairs

Intelligent nursing wheelchairs significantly enhance mobility and independence for elderly individuals with disabilities. However, traditional designs often suffer from large turning radii that restrict their functionality in confined spaces. Addressing this critical challenge, this study introduces an innovative design utilizing a Mecanum wheel chassis that allows for omnidirectional movement, significantly improving maneuverability and stability. Our design incorporates independently controlled Mecanum wheels, overcoming traditional constraints and enhancing user autonomy. To address issues such as wheel spacing variations and hub center tilting, which can lead to slipping and inaccurate motion control, we developed a novel suspension system that stabilizes the chassis, minimizes slipping risks, and boosts motion control accuracy. Experimental validations, including shock absorption and positioning tests, demonstrate that our suspension system markedly enhances the wheelchair's control performance and stability, thereby providing users with enhanced precision and potentially improving their quality of life.

Microgravity induces overconfidence in perceptual decision-making

Does gravity affect decision-making? This question comes into sharp focus as plans for interplanetary human space missions solidify. In the framework of Bayesian brain theories, gravity encapsulates a strong prior, anchoring agents to a reference frame via the vestibular system, informing their decisions and possibly their integration of uncertainty. What happens when such a strong prior is altered? We address this question using a self-motion estimation task in a space analog environment under conditions of altered gravity. Two participants were cast as remote drone operators orbiting Mars in a virtual reality environment on board a parabolic flight, where both hyper- and microgravity conditions were induced. From a first-person perspective, participants viewed a drone exiting a cave and had to first predict a collision and then provide a confidence estimate of their response. We evoked uncertainty in the task by manipulating the motion's trajectory angle. Post-decision subjective confidence reports were negatively predicted by stimulus uncertainty, as expected. Uncertainty alone did not impact overt behavioral responses (performance, choice) differentially across gravity conditions. However microgravity predicted higher subjective confidence, especially in interaction with stimulus uncertainty. These results suggest that variables relating to uncertainty affect decision-making distinctly in microgravity, highlighting the possible need for automatized, compensatory mechanisms when considering human factors in space research.

Evaluation of Objective Functions for the Optimal Design of an Assistive Robot

The number of individuals with upper or lower extremities dysfunction (ULED) has considerably increased in the past few decades, resulting in a high economic burden for their families and society. Individuals with ULEDs require assistive robots to fulfill all their activities of daily living (ADLs). However, a theory for the optimal design of assistive robots that reduces energy consumption while increasing the workspace is unavailable. Thus, this research presents an algorithm for the optimal link length selection of an assistive robot mounted on a wheelchair to minimize the torque demands of each joint while increasing the workspace coverage. For this purpose, this research developed a workspace to satisfy a list of 18 ADLs. Then, three torque indices from the literature were considered as performance measures to minimize; the three torque measures are the quadratic average torque (QAT), the weighted root square mean (WRMS), and the absolute sum of torques (AST). The proposed algorithm evaluates any of the three torque measures within the workspace, given the robot dimensions. This proposed algorithm acts as an objective function, which is optimized using a genetic algorithm for each torque measure. The results show that all tree torque measures are suitable criteria for assistance robot optimization. However, each torque measures yield different optimal results; in the case of the QAT optimization, it produces the least workspace with the minimum overall torques of all the joints. Contrarily, the WRMS and AST optimization yield similar results generating the maximum workspace coverage but with a greater overall torque of all joints. Thus, the selection between the three methods depends on the designer's criteria. Based on the results, the presented methodology is a reliable tool for the optimal dimensioning of assistive robots.

Adaptive control of a wheelchair mounted robotic arm with neuromorphically integrated velocity readings and online-learning

Wheelchair-mounted robotic arms support people with upper extremity disabilities with various activities of daily living (ADL). However, the associated cost and the power consumption of responsive and adaptive assistive robotic arms contribute to the fact that such systems are in limited use. Neuromorphic spiking neural networks can be used for a real-time machine learning-driven control of robots, providing an energy efficient framework for adaptive control. In this work, we demonstrate a neuromorphic adaptive control of a wheelchair-mounted robotic arm deployed on Intel’s Loihi chip. Our algorithm design uses neuromorphically represented and integrated velocity readings to derive the arm’s current state. The proposed controller provides the robotic arm with adaptive signals, guiding its motion while accounting for kinematic changes in real-time. We pilot-tested the device with an able-bodied participant to evaluate its accuracy while performing ADL-related trajectories. We further demonstrated the capacity of the controller to compensate for unexpected inertia-generating payloads using online learning. Videotaped recordings of ADL tasks performed by the robot were viewed by caregivers; data summarizing their feedback on the user experience and the potential benefit of the system is reported.

Embodied neuromorphic intelligence

The design of robots that interact autonomously with the environment and exhibit complex behaviours is an open challenge that can benefit from understanding what makes living beings fit to act in the world. Neuromorphic engineering studies neural computational principles to develop technologies that can provide a computing substrate for building compact and low-power processing systems. We discuss why endowing robots with neuromorphic technologies - from perception to motor control - represents a promising approach for the creation of robots which can seamlessly integrate in society. We present initial attempts in this direction, highlight open challenges, and propose actions required to overcome current limitations.