Socially Compliant Human-Robot Interaction for Autonomous Scanning Tasks in Supermarket Environments

Lewandowski, Benjamin; Wengefeld, Tim; Müller, Sabine; Jenny, Mathias; Glende, Sebastian; Schröter, Christof; Bley, A.; Groß, Horst–Michael

doi:10.1109/ro-man47096.2020.9223568

Cited by 21 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kanda et al, 2010;Shi et al, 2016) and increase shopping frequencies (e.g. Lewandowski et al, 2020), the robot was mostly seen by adults as a kids' mascot (Sabelli and Kanda, 2016). Thus, to be successful, the robot should have a clear purpose when interacting with potential customers, which is dependent on the goal (e.g.…”

Section: Placement Of Entertaining Robots In Retailingmentioning

confidence: 99%

“…When looking at the stages individually, the following could be concluded: studies only covering one phase of the funnel have addressed stopping power (Heikkil€ a et al, 2019;Sabelli and Kanda, 2016), engaging power (Zibafar et al, 2019;Neves et al, 2017;Aaltonen et al, 2017;Nakagawa et al, 2013) and attraction power (Kamei et al, 2010). Four studies have covered two stages of the funnel: stopping and engaging power (Shiomi et al, 2013;Gross et al, 2009), stopping and attraction power (Shi et al, 2016) or stopping and selling power (Lewandowski et al, 2020). Three studies have covered three stages of the funnel: while Kanda et al (2010) Using the robot (Iwamura et al, 2011;Gross et al, 2009) Initiating an interaction/communicating with robot (Iwasaki et al, 2018;Gross et al, 2009) ■ Looking at the store (Zibafar et al, 2019) ■ Interest in shops/store (Neves et al, 2017;Gross et al, 2009) ■ Visiting frequency (Iwasaki et al, 2018) ■ Visiting frequency (Shi et al, 2016: Kanda et al, 2010 ■ Shopping frequency (Kanda et al, 2010) ■ Purchase behavior (Lewandowski et al, 2020) ■ Time in front of shelves (Kamei et al, 2010) ■ Shopping time…”

Section: Placement Of Entertaining Robots In Retailingmentioning

confidence: 99%

“…Four studies have covered two stages of the funnel: stopping and engaging power (Shiomi et al, 2013;Gross et al, 2009), stopping and attraction power (Shi et al, 2016) or stopping and selling power (Lewandowski et al, 2020). Three studies have covered three stages of the funnel: while Kanda et al (2010) Using the robot (Iwamura et al, 2011;Gross et al, 2009) Initiating an interaction/communicating with robot (Iwasaki et al, 2018;Gross et al, 2009) ■ Looking at the store (Zibafar et al, 2019) ■ Interest in shops/store (Neves et al, 2017;Gross et al, 2009) ■ Visiting frequency (Iwasaki et al, 2018) ■ Visiting frequency (Shi et al, 2016: Kanda et al, 2010 ■ Shopping frequency (Kanda et al, 2010) ■ Purchase behavior (Lewandowski et al, 2020) ■ Time in front of shelves (Kamei et al, 2010) ■ Shopping time (Iwamura et al, 2011) ■ Number of purchases (Iwasaki et al, 2018;Iwamura et al, 2011) ■ Initial responses and remarkable behavior towards robot (Heikillä et al, 2019;…”

Section: Placement Of Entertaining Robots In Retailingmentioning

confidence: 99%

“…Initiating an interaction/communicating with robot (Lewandowski et al, 2020;Shiomi et al, 2013) Stopping in front of store (Shi et al, 2016) ■ ■ Interest in shops/store (Aaltonen et al, 2016;Kanda et al, 2010) Printing coupons (Nakagawa et al, 2013; The main objective of this literature review was to identify the gaps in previous research on the impact of retail service robots on shopper behavior, which is addressed in the current paper. For a more comprehensive overview of research on service robots in retailing, we refer to De Gauquier et al (2020).…”

Section: Placement Of Entertaining Robots In Retailingmentioning

confidence: 99%

See 3 more Smart Citations

In or out? A field observational study on the placement of entertaining robots in retailing

Gauquier

Brengman

Willems

et al. 2021

IJRDM

View full text Add to dashboard Cite

PurposeThe purpose of this paper is to empirically investigate the role of the placement (i.e. location) of humanoid service robots (HSRs) for entertainment applications in retailing by inspecting a multitude of performance metrics along the point-of-sale conversion funnel.Design/methodology/approachThe study was conducted using unobtrusive observations at a Belgian chocolate store. In total, 42 h of video observation material was collected and analyzed, with an even spread over three conditions: (1) an HSR placed outside, (2) an HSR inside the store and (3) a control condition (no robot stimuli). All passersby and their interactions with the robot and the store were systematically coded and compared.FindingsThe study found that the better placement of HSRs (inside or outside the store) is contingent on the goals the retailer prioritizes. When the goal is to create awareness and interest toward the store, the HSR should be placed outside, as it has double the stopping power. To induce consumers to enter the store, placement of the HSR inside the store is the better option. Ultimately, however, in terms of the number of transactions and total amount spent, outside placement of the HSR outperforms inside placement.Research limitations/implicationsThis study was not able to verify the internal emotional/cognitive state of the passersby, as the method relied on unobtrusive camera observations. A longitudinal research design would be desirable to exclude potential bias due to the novelty effect.Originality/valueWhile research on robots in retail services is emerging, this study is the first to provide insights on how retailers can decide on the placement of robots inside or outside the store, depending on the particular goals they are aiming to reach at the point of purchase.

show abstract

Section: Placement Of Entertaining Robots In Retailingmentioning

confidence: 99%

Section: Placement Of Entertaining Robots In Retailingmentioning

confidence: 99%

Section: Placement Of Entertaining Robots In Retailingmentioning

confidence: 99%

Section: Placement Of Entertaining Robots In Retailingmentioning

confidence: 99%

See 2 more Smart Citations

In or out? A field observational study on the placement of entertaining robots in retailing

Gauquier

Brengman

Willems

et al. 2021

IJRDM

View full text Add to dashboard Cite

show abstract

“…Semantic scene perception and understanding is essential for mobile robots acting in various environments. In our research projects, covering public environments from supermarkets [1], [2] to hospitals [3], [4] and domestic applications [5], [6], our robots need to perform several tasks in parallel such as obstacle avoidance, semantic mapping, navigation to semantic entities, and person perception. Most of the tasks require to be handled in real time given limited computing and battery capabilities.…”

Section: Introductionmentioning

confidence: 99%

Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis

Seichter¹,

Köhler²,

Lewandowski³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Analyzing scenes thoroughly is crucial for mobile robots acting in different environments. Semantic segmentation can enhance various subsequent tasks, such as (semantically assisted) person perception, (semantic) free space detection, (semantic) mapping, and (semantic) navigation. In this paper, we propose an efficient and robust RGB-D segmentation approach that can be optimized to a high degree using NVIDIA TensorRT and, thus, is well suited as a common initial processing step in a complex system for scene analysis on mobile robots. We show that RGB-D segmentation is superior to processing RGB images solely and that it can still be performed in real time if the network architecture is carefully designed. We evaluate our proposed Efficient Scene Analysis Network (ESANet) on the common indoor datasets NYUv2 and SUNRGB-D and show that it reaches state-of-the-art performance when considering both segmentation performance and runtime. Furthermore, our evaluation on the outdoor dataset Cityscapes shows that our approach is suitable for other areas of application as well. Finally, instead of presenting benchmark results only, we show qualitative results in one of our indoor application scenarios.

show abstract