UPEC-LISSI INRIA                                                                                                                 

Program



08:50 - 09:00

Introduction and welcome

Session 1

09:00 - 10:00

Emel DemircanEmel Demircan
Human Performance and Robotics Lab., CSULB, USA

Title: Constraint-Consistent, Robotics-Based Musculoskeletal Control Framework for Human Motion Synthesis
Abstract Human motor performance is a key area of investigation in biomechanics, robotics, and machine learning. Understanding human neuromuscular control is important to synthesize prosthetic motions and ensure safe human-robot interaction. Building controllable biomechanical models through modeling and algorithmic tools from both robotics and biomechanics increases our scientific understanding of musculoskeletal mechanics and control. The resulting models can consequently help quantifying the characteristics of a subject’s motion and in designing effective treatments, like predictive simulations and motion training. Our objective is to explore how neural control dictates motor performance in humans by developing a computational framework that enables robotics-based control and simulation of the human musculoskeletal system. In this talk, we will present the modeling, control, and simulation components of this new framework with examples of applications in rehabilitation, robotics, and athletics. The current framework has promise to advance the field of rehabilitation robotics by deepening our scientific understanding of human motor performance dictated by musculoskeletal physics and neural control. Automated and real-time motion improvement and retraining, facilitated with such frameworks, promise to transform the neuromuscular health, longevity, and independence of millions of people, utilizing a cost effective approach.
Joydeep BiswasJoydeep Biswas
AMRL, UMass Amherst, USA

Title: Deploying Autonomous Service Mobile Robots, And Keeping Them Autonomous
Abstract We seek the ultimate goal of having self-sufficient autonomous service mobile robots working in human environments, performing tasks accurately and robustly. Successfully deploying such robots requires addressing several challenges in mapping, localization, navigation, and autonomous exception recovery. The key to robust execution in all these sub-problems is to expect and anticipate changes in the environment, the deployment conditions, and algorithmic limitations. In this talk, I shall present our recent research along two broad themes: algorithms for robust navigation of long-term autonomous mobile robots, and algorithms to ensure that they remain autonomous over extended periods of time. In particular, I shall present several algorithms for long-term mapping, localization, joint perception and planning, and autonomous sensor calibration. These algorithms have enabled our robots to autonomously traversal more than a thousand kilometers while performing tasks in multiple universities.

10:00 - 10:30

Coffee break 30'

Session 2

10:30 - 12:30

Yuhang CheYuhang Che
CHARM Lab, Stanford, USA

Title: Haptic Communication for Human-Mobile Robot Interaction
Abstract Mobile robots have great potential in home applications such as personal assistant, home cleaning, and elderly care. Besides accomplishing such tasks autonomously, these robots need to interact and communicate with people. Our object is to explore the use of haptic feedback to facilitate communication between human users and mobile robots. We first present our design and evaluation of a “virtual tether” system for a mobile robot assistant that follows a person. The virtual tether can establish two-way communication that provides the robot's status to the user and enables the user to direct the robot when necessary (e.g., when the robot fails to follow the user due to unexpected obstacles). The tether system consists of a haptic interface that displays touch cues to convey the robot's status via asymmetric vibration and a command interface for teleoperating the robot follower. We tested the virtual tether system in user studies with a physical robot follower and showed that users can focus on their task better, respond to robot failure events faster, and adapt to the robot's limitations with the tether system. We then explore the application of haptic communication in indoor robot navigation. We showed that by using haptic feedback to convey high level intent of the robot, human's response to the robot movement can be altered. A simple predictive model was derived using experimental data, and we discussed how it can be incorporated in robot motion planning.
Francesco ReaFrancesco Rea
IIT-RBCS, Genova, Italy

Title: Models of human-humanoid interaction: interaction strategies adaptable to untrained user
Abstract Assistive Robotics, especially if designed to support frail people and people with cognitive disabilities, requires a wide range of capabilities, at present, only partially exploited in the context of unstructured scenarios. The study of models of human-human interaction can indicate which skills the new generation of assistive robots should exhibit to promote dependable assistance. The porting of such interaction models on service robots, enable intuitive and effective human-robot interaction that makes people comfortable with the robotic assistance. The result leverages on elementary forms of interaction, familiar to most of the untrained users, thus avoiding specific training to use the technology or uncanny experiences . In particular, these models rely on mutual understanding between the human and the robot and build on communication strategies based on essential social signaling. We will go through an overview of the robot abilities necessary to engage with the assisted person, recent achievements in human-robot interaction (e.g.: social robotics and affective computing) focusing on the context of assistance to humans in unstructured environments and insights on our recent experience in providing assistive robotic technology for frail people, in particular persons with cognitive disabilities and elderly people.
Interactive session (contributed papers) (4×15')
Authors: Mohammed Kutbi, Yizhe Chang and Philippos Mordohai
Title: Hands-free Wheelchair Navigation Based on Egocentric Computer Vision: A Usability Study
Authors: Alexander Poeppel, Alwin Hoffmann, Martin Siehler and Wolfgang Reif
Title: Intelligent Capacitive Sensing for Human-Robot-Interaction using Neural Networks: Towards Flexible Production Systems
Authors: Zackory Erickson, Maggie Collier, Ariel Kapusta and Charles Kemp
Title: Investigating Capacitive Proximity Sensing for Tracking Human Pose During Robot-Assisted Dressing

»Authors: Nicolas Drougard, Caroline P. Carvalho Chanel, Raphaelle N. Roy and Frédéric Dehais
Title: Mixed-initiative mission planning considering human operator state estimation based on physiological sensors
>

Authors: Xuefeng Bao, Zhiyu Sheng and Nitin Sharma
Title: A Tube-based Model Predictive Control Method for Sharing Control Inputs in a Hybrid Neuroprosthesis

12:30 - 14:00

Lunch 1h30

Session 3

14:00 - 16:00

Siddartha SrinivasaSiddartha Srinivasa
Personal Robotics Lab., CMU, USA

Title: Assistive Feeding: A New Challenge for Manipulation and Shared Autonomy
Abstract There are over 12.3 million people in the United States who need assistance with one or more activities of daily living (ADLs). Key among them is feeding, which is both time-consuming for the caregiver, and challenging for the care recipient to accept socially. At the Personal Robotics Lab at the University of Washington, we have been developing an end-to-end system for assistive feeding, with the goal of achieving the same level of dexterity, effortlessness, and seamlessness as an able-bodied human. In this talk, I will describe some of our latest efforts at manipulating food for bite acquisition, and understanding social dining for bite timing, and discuss several challenges and open technical and practical problems.
Norihiro HagitaNorihiro Hagita
ATR Intelligent Robotics and Communication Laboratories

Title: Autonomous Personal Mobility Services in Human Environments Using Smart Networked Robotics
Abstract This talk introduces recent works and ELSE (Ethical, Legal, Social and Economic) challenges on social intelligence for robotic services in human environments, i.e. shopping mall, food court, information center. It focuses on a field experiment for autonomous wheelchairs allowing safety riding while the passengers are talking to each other. As ELSE challenges, it also shows a common sense to be considered for service robots performing various tasks in the area. It introduces a easy-to-use method for end-users who typically have no programming expertise to easily input utterance contents and behaviors to service robots. Finally, it would discuss the perspectives of ELSE challenges for assistance and service robotics in urban area.
Marie BabelMarie Babel
INSA Rennes, Irisa, France

Title: Smart wheelchairs: the tomorrow's vehicles?
Abstract The global ageing population, along with disability compensation constitute major challenging societal and economic issues. In particular, achieving autonomy remains a fundamental need that contributes to the individual’s wellness and well-being. In this context, innovative and smart technologies are designed to achieve independence while matching user’s individual needs and desires. Hence, designing a robotic assistive solution related to wheelchair navigation remains of major importance as soon as it compensates partial incapacities. In particular, the idea is to design an indoor / outdoor efficient obstacle avoidance system that respects the user intention, and does not alter user perception. To this aim, we proposed a unified shared control framework able to smoothly correct the trajectory of the electrical wheelchair. The system integrates the manual control with sensor-based constraints by means of a dedicated optimization strategy. In addition, the acceptability of assistive devices has to be carefully observed. Enhancing the Quality of Experience related to the use of assistive devices remains a challenge. A way to address this issue is to design adapted interfaces that provide biofeedbacks such as adapted haptic feedback that augment the user cognitive abilities. Considering the social acceptability, if assistive technology naturally empowers and enables people to travel, work, socialize, misperceptions remain social barriers to accessibility. In the context of social robotics such as wheelchair navigation, human-aware navigation should then match social conventions. In short, we aim at augmenting a standard assistive device such as a wheelchair to become smart, connected and collaborative with the users in achieving everyday living tasks.
Alberto ParmiggianiAlberto Parmiggiani
IIT-ICUB, Genova, Italy

Title: R1: towards affordable personal humanoids
Abstract In the last five years the robotics field has witnessed a major transformation. More and more companies are starting to provide service robots intended to cooperate with humans. The robots developed so far are in general either rather costly, or unsuitable for manipulation tasks. This article presents the result of a project aimed at demonstrating the feasibility of an affordable humanoid robot. The application of this technology, generally speaking, is directed at the improvement of the quality of everyday life. Our ballpark figure for the final cost of the robot is in the range of a family car and, possibly, when produced in large quantities, a significantly lower one. This goal has been tackled from three synergistic directions: with the use of polymeric materials, light-weight design and by implementing novel actuation solutions. These points as well as the robot and its main features will be described in the presentation.

16:00 - 16:30

Coffee break 30'

Session 4

16:30 - 17:30

Nitin SharmaNitin Sharma
Neuromuscular Control and Robotics Laboratory, Pittsburg, USA

Title: Human Motor Control Inspired Controller to Compensate for Actuator Redundancy in a Hybrid Neuroprosthesis
Abstract To restore walking and standing function in persons with paraplegia, a hybrid walking neuroprosthesis that combines a powered exoskeleton and functional electrical stimulation (FES) can be more advantageous than sole FES or powered exoskeleton technologies. However, the hybrid actuation structure introduces certain control challenges: actuator redundancy, cascaded muscle activation dynamics, FES-induced muscle fatigue, and unmeasurable states. The talk focuses on a human motor control inspired control scheme which is combined with a dynamic surface control method to overcome these challenges. The new controller has an adaptive muscle synergy-based feedforward component which requires a fewer number of control signals to actuate multiple effectors in a hybrid neuroprosthesis. The experimental results on a person with spinal cord injury and an able-bodied participant will be presented.
Brenna ArgallBrenna Argall
Assistive and Rehabilitation Robotics Laboratory, NWU, USA

Title: Bridging Gaps in Lost Human Function with Shared Autonomy Robotics
Abstract It is an irony that often the more severe a person's motor impairment, the more challenging it is for them to operate the very assistive machines which might enhance their quality of life. To introduce robotics autonomy and intelligence offers a solution that can offload some control burden from the operator, helping to bridge gaps left by sensory, motor or cognitive impairments in the users of assistive machines. However, here the human-robot team is a very particular one: the robot is physically supporting or attached to the human, replacing or enhancing lost or diminished function. In this case getting the allocation of control between the human and robot right is absolutely essential, and will be critical for the adoption of physically assistive robots within larger society. This talk will overview a selection of our projects and studies that aim to introduce autonomy that is both judicious and customized to an individual’s physical abilities and personal preferences.

17:30 - 17:40

Closing remarks