Visual Goal Human-Robot Communication Framework With Few-Shot Learning: A Case Study in Robot Waiter System

Sawadwuthikul, Guntitat; Tothong, Tanyatep; Lodkaew, Thanawat; Soisudarat, Puchong; Nutanong, Sarana; Manoonpong, Poramate; Dilokthanakul, Nat

doi:10.1109/tii.2021.3049831

Cited by 23 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The development of e-commerce and logistics industry has promoted the integrated application of intelligent handling robots in automated warehouses and promoted the transformation and upgrading of storage operation mode. However, a series of problems about intelligent and efficient task allocation, vehicle scheduling, path planning, and conflict handling restrict the promotion and application of handling robots [5]. Therefore, it is necessary to increase the research on the handling robot, solve the technical difficulties affecting the integrated application of the handling robot, and realize the cooperative planning of multiple handling robots, so as to improve the operating efficiency, reduce labor costs, and maximize profits.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Path Planning Analysis of Warehouse Handling Robot

Zhao

2022

Journal of Sensors

View full text Add to dashboard Cite

In order to further improve the operational efficiency and the flexibility of automated warehouse, a path planning algorithm for a warehouse handling robot was evaluated. Under the background of determining the operation scene and environment of multihandling robot, a path planning algorithm with time window is proposed for multihandling robot, and a two-stage path planning method is also analyzed. The results show that the route planning using the improved Dijkstra algorithm saves 7.16 meters compared with the traditional algorithm, and the task is completed 3.17 seconds earlier. Comprehensively considering the heat of the various paths to turn to the required time, using the improved Dijkstra algorithm path, handling the robot’s total running distance than the traditional algorithm saves 14.45 meters, the total run time saves 8.45 seconds, and whether in time or in the distance, crane robot handling efficiency compared with the traditional algorithm has an obvious increase, closer to reality.

show abstract

Section: Introductionmentioning

confidence: 99%

Dynamic Path Planning Analysis of Warehouse Handling Robot

Zhao

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Yet, the focus of this work was to only model correct waiter behaviour, without any adaptation. More recently, Sawadwuthikul et al [13] sought to improve on these static behaviour policies through dynamic adaptation of positioning and trajectory by learning from a human-in-the-loop. Human feedback was only used to assist the robots' ability to remember the location of a customer when several customers were present.…”

Section: A Humanoid Service Robotsmentioning

confidence: 99%

“…Yet, real-time adaptation in social robots is still relatively less explored. Recent works have shown that robots are able to learn socially appropriate behaviours through a combination of feedback mechanisms, which might include implicit, explicit or pre-trained behaviours [13], [20], [24]. Implicit signal processing in HRI, such as evaluating facial expressions [25] or body language, allows for more feedback to be collected from the participant, and also reduces 'feedback fatigue' [26]- [28].…”

Section: B Learning Socially Appropriate Behaviours In Hrimentioning

confidence: 99%

Learning Socially Appropriate Robo-waiter Behaviours through Real-time User Feedback

McQuillin

Churamani

Güneş

2022

2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

Current Humanoid Service Robot (HSR) behaviours mainly rely on static models that cannot adapt dynamically to meet individual customer attitudes and preferences. In this work, we focus on empowering HSRs with adaptive feedback mechanisms driven by either implicit reward, by estimating facial affect, or explicit reward, by incorporating verbal responses of the human 'customer'. To achieve this, we first create a custom dataset, annotated using crowd-sourced labels, to learn appropriate approach (positioning and movement) behaviours for a Robowaiter. This dataset is used to pre-train a Reinforcement Learning (RL) agent to learn behaviours deemed socially appropriate for the robo-waiter. This model is later extended to include separate implicit and explicit reward mechanisms to allow for interactive learning and adaptation from user social feedback. We present a within-subjects Human-Robot Interaction (HRI) study with 21 participants implementing interactions between the robowaiter and human customers implementing the above-mentioned model variations. Our results show that both explicit and implicit adaptation mechanisms enabled the adaptive robo-waiter to be rated as more enjoyable and sociable, and its positioning relative to the participants as more appropriate compared to using the pre-trained model or a randomised control implementation.

show abstract

“…In human-populated environments mobility of robots involves sharing the same physical space, engaging in social interactions with humans, and following the social norms. Moreover, acceptance of the robots will also depend upon factors like trust, safety, and likability of robots among humans [7][8][9][10]. So, the most vital aspect in developing robots for humanpopulated environments is the integration of strategies that allows them to navigate in a socially acceptable way.…”

Section: Introductionmentioning

confidence: 99%

Behavior of Delivery Robot in Human-Robot Collaborative Spaces During Navigation

Singh¹,

Kapoor²,

Abouhawwash³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Navigation is an essential skill for robots. It becomes a cumbersome task for the robot in a human-populated environment, and Industry 5.0 is an emerging trend that focuses on the interaction between humans and robots. Robot behavior in a social setting is the key to human acceptance while ensuring human comfort and safety. With the advancement in robotics technology, the true use cases of robots in the tourism and hospitality industry are expanding in number. There are very few experimental studies focusing on how people perceive the navigation behavior of a delivery robot. A robotic platform named "PI" has been designed, which incorporates proximity and vision sensors. The robot utilizes a real-time object recognition algorithm based on the You Only Look Once (YOLO) algorithm to detect objects and humans during navigation. This study is aimed towards evaluating human experience, for which we conducted a study among 36 participants to explore the perceived social presence, role, and perception of a delivery robot exhibiting different behavior conditions while navigating in a hotel corridor. The participants' responses were collected and compared for different behavior conditions demonstrated by the robot and results show that humans prefer an assistant role of a robot enabled with audio and visual aids exhibiting social behavior. Further, this study can be useful for developers to gain insight into the expected behavior of a delivery robot.

show abstract

Visual Goal Human-Robot Communication Framework With Few-Shot Learning: A Case Study in Robot Waiter System

Cited by 23 publications

References 19 publications

Dynamic Path Planning Analysis of Warehouse Handling Robot

Dynamic Path Planning Analysis of Warehouse Handling Robot

Learning Socially Appropriate Robo-waiter Behaviours through Real-time User Feedback

Behavior of Delivery Robot in Human-Robot Collaborative Spaces During Navigation

Contact Info

Product

Resources

About