Papers
Topics
Authors
Recent
Search
2000 character limit reached

Lio -- A Personal Robot Assistant for Human-Robot Interaction and Care Applications

Published 16 Jun 2020 in cs.RO, cs.AI, and cs.HC | (2006.09019v1)

Abstract: Lio is a mobile robot platform with a multi-functional arm explicitly designed for human-robot interaction and personal care assistant tasks. The robot has already been deployed in several health care facilities, where it is functioning autonomously, assisting staff and patients on an everyday basis. Lio is intrinsically safe by having full coverage in soft artificial-leather material as well as having collision detection, limited speed and forces. Furthermore, the robot has a compliant motion controller. A combination of visual, audio, laser, ultrasound and mechanical sensors are used for safe navigation and environment understanding. The ROS-enabled setup allows researchers to access raw sensor data as well as have direct control of the robot. The friendly appearance of Lio has resulted in the robot being well accepted by health care staff and patients. Fully autonomous operation is made possible by a flexible decision engine, autonomous navigation and automatic recharging. Combined with time-scheduled task triggers, this allows Lio to operate throughout the day, with a battery life of up to 8 hours and recharging during idle times. A combination of powerful on-board computing units provides enough processing power to deploy artificial intelligence and deep learning-based solutions on-board the robot without the need to send any sensitive data to cloud services, guaranteeing compliance with privacy requirements. During the COVID-19 pandemic, Lio was rapidly adjusted to perform additional functionality like disinfection and remote elevated body temperature detection. It complies with ISO13482 - Safety requirements for personal care robots, meaning it can be directly tested and deployed in care facilities.

Citations (129)

Summary

  • The paper demonstrates Lio's design as a mobile robot platform that integrates multi-sensor fusion and a compliant robotic arm to safely perform care tasks.
  • It details an autonomous decision engine and a ROS-enabled infrastructure that supports object manipulation, remote monitoring, and specialized tasks like UV-C disinfection.
  • Real-world deployments show Lio achieving an 85.5% success rate in autonomous deliveries and effectively aiding patient independence in healthcare settings.

Overview of Lio - A Personal Robot Assistant for Human-Robot Interaction and Care Applications

The paper presents Lio, a mobile robot platform developed to enhance human-robot interaction and assist in personal care tasks within healthcare settings. Designed by the team at F&P Robotics AG in Zurich, Lio is an embodiment of sophisticated robotic engineering incorporating a multi-functional arm and advanced navigation capabilities supported by a rich array of sensors.

Technical Specifications

Lio is equipped with a variety of sensors optimized for robust environmental interaction. These include visual, audio, laser, ultrasound, and mechanical sensors, integral for navigation and object manipulation. Offering a ROS-enabled platform, Lio provides researchers with the ability to access raw sensor data and direct control of the robot, showcasing the emphasis on flexibility and customizability.

The robotic arm of Lio, a significant differentiator in care robotics, extends the scope of interaction beyond simple social interactions to include object manipulation, such as opening doors and handling items. Padded with artificial leather for intrinsic safety, Lio operates within strict limits on speed and force, incorporating a compliant motion controller to handle real-world interactions safely.

Autonomous Capabilities and Software Infrastructure

Lio operates autonomously, enabled by a decision engine that navigates healthcare facilities and home environments without significant alterations. The onboard processing capabilities allow the deployment of deep learning algorithms without the reliance on cloud services, ensuring privacy—a pivotal aspect in healthcare settings.

The paper details how Lio can execute tasks such as remote monitoring, UV-C disinfection, and elevated body temperature detection—a feature rapidly incorporated during the COVID-19 pandemic. This adaptability highlights the robot's potential to evolve alongside changing healthcare demands.

Different software interfaces, namely myP and ROS, provide diverse access points for varying levels of user expertise, from technical developers to healthcare staff. The modularity of the software system is notable, supporting both predefined and custom routines tailored to specific institutional needs.

Practical Implications and Use Cases

Deployed in several health care facilities across Switzerland and Germany, Lio performs a range of tasks from logistical deliveries to patient interactions. The robot's application in a real-world scenario underscores its utility, with mixed task performance, such as driving significant distances autonomously for delivery missions with an average success rate of 85.5%.

Furthermore, trials with individuals with mobility challenges demonstrate Lio’s potential to foster independence, enhancing life quality by assisting with personal tasks.

Evaluation and Limitations

Usability studies are integral to the ongoing development and deployment of Lio. Analysis of real-world deployments contributes to iterative improvements addressing issues such as complex environment navigation and varying interaction dynamics with elderly and disabled users.

The paper recognizes limitations, such as reliance on preset markers for certain tasks and challenges in cluttered environments, indicating areas for future refinement.

Conclusions and Prospects

The research introduces Lio as a comprehensive platform for care robotics, emphasizing its compliance with safety standards, which is pivotal for integration into sensitive environments like healthcare. The flexibility in software architecture allows Lio to be an ideal candidate for further research and development in human-robot interaction.

Future directions include enhancing multi-floor navigation, improving proactive interaction strategies, and integrating more sophisticated natural language processing capabilities. These advancements could see Lio transitioning from a supportive to a more autonomous, pro-active participant in caregiving and daily activities.

In conclusion, Lio represents a significant step towards the broader integration of robotics in care settings. Continuous improvements and an openness to adaptation to emerging healthcare challenges position Lio as a valuable asset in addressing workforce constraints and improving patient care standards.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.