In‐the‐loop or on‐the‐loop? Interactional arrangements to support team coordination with a planning agent

Fischer, Joel E.; Greenhalgh, Chris; Jiang, Wenchao; Ramchurn, Sarvapali D.; Wu, Feng; Rodden, Tom

doi:10.1002/cpe.4082

Cited by 20 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DroneResponse deploys multiple sUAS to support emergency response missions [6], [7], [28]. It is designed as a HoTL system empowered to make and enact decisions [4] supported by its onboard CV. Enabling higher degrees of autonomy is particularly important in DroneResponse missions, where multiple sUAS are deployed simultaneously to perform time-constrained search-and-rescue, surveillance, or delivery tasks.…”

Section: Cv-supported Autonomymentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Autonomy in Human-on-the-Loop Vision-Based Robotics Systems

Abraham¹,

Carmichael²,

Banerjee³

et al. 2021

Preprint

View full text Add to dashboard Cite

Computer vision approaches are widely used by autonomous robotic systems to sense the world around them and to guide their decision making as they perform diverse tasks such as collision avoidance, search and rescue, and object manipulation. High accuracy is critical, particularly for Human-on-the-loop (HoTL) systems where decisions are made autonomously by the system, and humans play only a supervisory role. Failures of the vision model can lead to erroneous decisions with potentially life or death consequences. In this paper, we propose a solution based upon adaptive autonomy levels, whereby the system detects loss of reliability of these models and responds by temporarily lowering its own autonomy levels and increasing engagement of the human in the decision-making process. Our solution is applicable for vision-based tasks in which humans have time to react and provide guidance. When implemented, our approach would estimate the reliability of the vision task by considering uncertainty in its model, and by performing covariate analysis to determine when the current operating environment is illmatched to the model's training data. We provide examples from DroneResponse, in which small Unmanned Aerial Systems are deployed for Emergency Response missions, and show how the vision model's reliability would be used in addition to confidence scores to drive and specify the behavior and adaptation of the system's autonomy. This workshop paper outlines our proposed approach and describes open challenges at the intersection of Computer Vision and Software Engineering for the safe and reliable deployment of vision models in the decision making of autonomous systems.

show abstract

Section: Cv-supported Autonomymentioning

confidence: 99%

“…Human-on-the-loop (HoTL) systems are empowered to make and enact their own decisions [4] with humans performing only a supervisory role [5]. Decisions are supported by the system's knowledge of the environment, which is often acquired using CV.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Autonomy in Human-on-the-Loop Vision-Based Robotics Systems

Abraham¹,

Carmichael²,

Banerjee³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…While for example occupancy-sensitive home automation has been explored [29], our work seeks to draw attention to the numerous remaining challenges concerning how to best bring the human back into the loop [58].…”

Section: Design Challengesmentioning

confidence: 99%

Breaching the Future: Understanding Human Challenges of Autonomous Systems for the Home

et al. 2018

View full text Add to dashboard Cite

The domestic environment is a key area for the design and deployment of autonomous systems. Yet research indicates their adoption is already being hampered by a variety of critical issues including trust, privacy and security. This paper explores how potential users relate to the concept of autonomous systems in the home and elaborates further points of friction. It makes two contributions. The first one is of a methodological nature and focuses on the use of provocative utopian and dystopian scenarios of future autonomous systems in the home. These are used to drive an innovative workshop-based approach to breaching experiments, which surfaces the usually tacit and unspoken background expectancies implicated in the organisation of everyday life that have a powerful impact on the acceptability of future and emerging technologies. The other contribution is substantive, produced through participants' efforts to repair the incongruity or Breality disjuncture^created by utopian and dystopian visions, and highlights the need to build social as well as computational accountability into autonomous systems, and to enable coordination and control. Keywords Autonomous systems . Domestic environment . Background expectancies . Breaching experiments . Scenarios . Utopian and dystopian contra-visions . Reality disjunctures

show abstract

“…The UAVs of next-generation emergency response systems will be capable of sensing, planning, reasoning, sharing, and acting to accomplish their tasks [6]. These UAVs will not require humans-in-the-loop to make all key decisions, but rather will make independent decisions with humans-on-the-loop setting goals and supervising the mission [7]. For example, in a multi-UAV river search-and-rescue mission, the autonomous UAV can detect a drowning person in the river utilizing the on-board AI vision models (sensing) and ask another UAV to schedule delivery of a flotation device to the victim's location (planning and reasoning).…”

Section: Introductionmentioning

confidence: 99%

Model-Driven Requirements for Humans-on-the-Loop Multi-UAV Missions

Agrawal¹,

Steghöfer²,

Cleland‐Huang³

2020

Preprint

View full text Add to dashboard Cite

The use of semi-autonomous Unmanned Aerial Vehicles (UAVs or drones) to support emergency response scenarios, such as fire surveillance and search-and-rescue, has the potential for huge societal benefits. Onboard sensors and artificial intelligence (AI) allow these UAVs to operate autonomously in the environment. However, human intelligence and domain expertise are crucial in planning and guiding UAVs to accomplish the mission. Therefore, humans and multiple UAVs need to collaborate as a team to conduct a time-critical mission successfully. We propose a meta-model to describe interactions among the human operators and the autonomous swarm of UAVs. The meta-model also provides a language to describe the roles of UAVs and humans and the autonomous decisions. We complement the meta-model with a template of requirements elicitation questions to derive models for specific missions. We also identify common scenarios where humans should collaborate with UAVs to augment the autonomy of the UAVs. We introduce the meta-model and the requirements elicitation process with examples drawn from a search-and-rescue mission in which multiple UAVs collaborate with humans to respond to the emergency. We then apply it to a second scenario in which UAVs support first responders in fighting a structural fire. Our results show that the metamodel and the template of questions support the modeling of the human-on-the-loop human interactions for these complex missions, suggesting that it is a useful tool for modeling the human-on-the-loop interactions for multi-UAVs missions.

show abstract

In‐the‐loop or on‐the‐loop? Interactional arrangements to support team coordination with a planning agent

Cited by 20 publications

References 28 publications

Adaptive Autonomy in Human-on-the-Loop Vision-Based Robotics Systems

Adaptive Autonomy in Human-on-the-Loop Vision-Based Robotics Systems

Breaching the Future: Understanding Human Challenges of Autonomous Systems for the Home

Model-Driven Requirements for Humans-on-the-Loop Multi-UAV Missions

Contact Info

Product

Resources

About