Blending human and robot inputs for sliding scale autonomy

Desai, Munjal; Yanco, Holly A.

doi:10.1109/roman.2005.1513835

Cited by 45 publications

(36 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Blending human and robot policies via a generic function has also been proposed by (Enes and Book, 2010). (Desai and Yanco, 2005) proposed a linear blend in two dimension between maximum user speed and maximum robot speed. Outside the teleoperation domain, a type of arbitration -averaging -is used for mediating between two human input channels (Glynn and Henning, 2000), and blending in general between two human policies is used in surgery training (Nudehi et al, 2005).…”

Section: Prior Workmentioning

confidence: 99%

A policy-blending formalism for shared control

Dragan

Srinivasa

2013

The International Journal of Robotics Research

298

312

View full text Add to dashboard Cite

Abstract-In shared control teleoperation, the robot assists the user in accomplishing the desired task, making teleoperation easier and more seamless. Rather than simply executing the user's input, which is hindered by the inadequacies of the interface, the robot attempts to predict the user's intent, and assists in accomplishing it. In this work, we are interested in the scientific underpinnings of assistance: we propose an intuitive formalism that captures assistance as policy blending, illustrate how some of the existing techniques for shared control instantiate it, and provide a principled analysis of its main components: prediction of user intent and its arbitration with the user input. We define the prediction problem, with foundations in Inverse Reinforcement Learning, discuss simplifying assumptions that make it tractable, and test these on data from users teleoperating a robotic manipulator. We define the arbitration problem from a control-theoretic perspective, and turn our attention to what users consider good arbitration. We conduct a user study that analyzes the effect of different factors on the performance of assistance, indicating that arbitration should be contextual: it should depend on the robot's confidence in itself and in the user, and even the particulars of the user. Based on the study, we discuss challenges and opportunities that a robot sharing the control with the user might face: adaptation to the context and the user, legibility of behavior, and the closed loop between prediction and user behavior.

show abstract

Section: Prior Workmentioning

confidence: 99%

A policy-blending formalism for shared control

Dragan

Srinivasa

2013

The International Journal of Robotics Research

298

312

View full text Add to dashboard Cite

show abstract

“…Sometimes, the term sliding autonomy is used to indicate one or a mixture of the three above [21]. Sliding scale autonomy [20] relaxes discrete LOA to a continuum of assistance. Additionally, prevailing shared control approaches such as potential field methods [2], virtual fixture based methods [25], [1], and haptic shared control [14] are ultimately rooted in LOA/FA.…”

Section: Related Workmentioning

confidence: 99%

Breaking the Human-Robot Deadlock: Surpassing Shared Control Performance Limits with Sparse Human-Robot Interaction

Trautman

2017

Robotics: Science and Systems XIII

View full text Add to dashboard Cite

Abstract-Human machine teaming has, for decades, been conceptualized as a function allocation (FA) or levels of autonomy (LOA) process: the human is suited for some tasks, while the machine is suitable for others, and as machines improve they take over duties previously assigned to humans. A wide variety of methods-including adaptive, adjustable, blended, supervisory and mixed initiative control, implemented discretely or continuously, as potential fields, as virtual fixture interfaces, or haptic interfaces-are derivatives of FA/LOA. We formalize FA/LOA (and all their derivatives) under a single mathematical formulation called classical shared control (CSC). Despite the widespread adoption of CSC, we prove that it fails to optimize human and robot agreement and intent if either the human or robot model displays "intention ambiguity" (e.g., the human's intended goal is unclear or the robot finds multiple viable solutions). Practically, this suboptimality can manifest as unnecessary and unresolvable disagreement (an unnecessary deadlock). For instance, if the robot chooses to go left around an obstacle and the human chooses to go right, CSC only provides two solutions: freeze in place or collide with the obstacle (we provide a wide variety of failure examples in [52], https://arxiv.org/abs/1611.09490). We find that CSC suboptimality stems from arbitrating over model samples, rather than over models. Our key insight is thus to arbitrate over human and robot distributions; we prove this method optimizes human and robot agreement and intent and resolves deadlocking. Our key contribution is computationally efficient distribution arbitration: if the human and robot carry N our joint has fewer modes than the individual agent models. We call our approach N min -sparse generalized shared control.

show abstract

“…• Adjustable autonomy addresses the issue of choosing autonomy levels appropriate to preference, trust, skill level, or the demands of a given situation [6,15]. Most strategies considered in the current work fall within the shared control model and respond to erroneous commands by halting or resisting motion.…”

Section: Related Workmentioning

confidence: 99%

Assisted Teleoperation Strategies for Aggressively Controlling a Robot Arm with 2D Input

You¹,

Hauser²

2011

Robotics: Science and Systems VII

View full text Add to dashboard Cite

Abstract-This paper studies assisted teleoperation techniques for controlling a 6DOF robot arm using click-and-drag input from a computer mouse. Experiments were conducted to investigate how task performance and user preferences are affected by low-level motion control strategies, which must deal with collision avoidance, dynamics constraints, and erroneous input. Five strategies were implemented and compared. As baseline strategies we study direct joint control and Cartesian positioning via inverse kinematics. We also implemented three obstacle avoidance strategies, including a predictive safety filter, a reactive potential field, and a real-time sample-based motion planner. Blind experimental trials assigned 22 novice subjects to five subgroups corresponding to each strategy and asked them to control the arm in simulation on a variety of reaching tasks in cluttered environments. Unsurprisingly, the obstacle avoidance strategies achieve major safety improvements, although subjects felt noticeably less in control of the robot than those using the baseline methods. The motion planning strategy shows the most promise; it completed tasks twice as fast as any other method and received high ratings for perceived safety, cooperativeness, and overall satisfaction.

show abstract

Blending human and robot inputs for sliding scale autonomy

Cited by 45 publications

References 5 publications

A policy-blending formalism for shared control

A policy-blending formalism for shared control

Breaking the Human-Robot Deadlock: Surpassing Shared Control Performance Limits with Sparse Human-Robot Interaction

Assisted Teleoperation Strategies for Aggressively Controlling a Robot Arm with 2D Input

Contact Info

Product

Resources

About