Prediction of users trajectories to mimic / avoid the customer behaviour during mapping tasks of an autonomous robot in retail environment

Maiolini, Jacopo; Rossi, Luca; Pietrini, Rocco; Mancini, Adriano; Frontoni, Emanuele; Zingaretti, Primo

doi:10.1109/mesa55290.2022.10004396

Cited by 1 publication

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since testing with robots and cameras in public environments such as supermarkets requires compliance with security and privacy constraint, the GAZEBO [25] robotic simulation toolbox was initially used. The dataset used to validate the proposed approach consists of four different stores located in Germany and Indonesia [23]. The map and the world that are necessary for the simulation of each individual store are inferred from the static map M as if it would be produced by gmapping [26] with binary occupancy probability: an occupancy probability of 100% with a black pixel and of 0% with a white pixel.…”

Section: Resultsmentioning

confidence: 99%

“…Shopper behavior understanding solutions currently employed is not however limited to active tracking systems, in fact by using cameras and advanced algorithms, vision-based systems can also track the trajectories of shoppers, and in addition recognize shopper interactions with the products (such as picking up an item, putting the item back, touching the item) [22] which can give even more valuable insights about shoppers behavioral patterns. Maiolini et al [23] proposed a strategy to predict the trajectory of shoppers inside a store that could be used by the navigation planner of a robot to map highly visited areas. The approach could be also used to avoid the customers during their shopping in order to minimize the bother caused by the presence of a mobile platform.…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, assuming to have fixed-mounted cameras on the robotic platform, which is often the case, it is necessary to calculate, for each shelf in the H raw map, the minimum distance d min from where the robot cameras can successfully enclose vertically the whole shelf. Given the height of the shelf s i and the camera properties (mounting point on the robot and vertical Field Of View (FOV)) the minimum capturing distance can be calculate as follows [23]:…”

Section: Problem Formulationmentioning

confidence: 99%

See 2 more Smart Citations

Retail Robot Navigation: A Shopper Behavior-Centric Approach to Path Planning

Galdelli,

Pietrini,

Mancini

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

In the ever-evolving landscape of retail, understanding shopper behavior is pivotal for optimizing sales and effectively managing product availability and placement. This study explores the integration of autonomous mobile robots into the shelf inspection process, leveraging advancements in automation, information, and robotics technology. Performing mapping tasks, these robots incorporate insights into customer behavior by exploiting various sources of behavioral data, including trajectories and product interactions. Motivated by the complex and dynamic nature of modern stores, our research seeks to bridge the gap in retail inventory management. Our unique contribution lies in the development of a novel path planning method for robots, specifically tailored for an automated inventory management system. By focusing on customer trajectories and product interactions, we aim to enhance the arrangement and positioning of products within retail spaces. Our research is motivated by the need to address the challenges faced by retailers in optimizing store layouts and product placements. The proposed strategy utilizes a heatmap and a vision-based system to analyze spatial and temporal patterns of shopper behavior. This information is then employed to optimize robot navigation in both highly and less-visited areas. Trajectories and product interactions data from real store installations were utilized in simulation, providing valuable insights into optimal planning for mobile robots to visit Points of Interest (PoI). The active shopping cart tracking system generated heatmaps, while a vision-based system collected shopper-products interactions data. Subsequently, our approach was deployed on a real retail robot for inventory management, and the path planning source code was released. Our findings demonstrate that the path planned by our approach not only avoids collisions with static store sections but also optimizes paths in areas with significant customer-shelf activity.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Problem Formulationmentioning

confidence: 99%

See 1 more Smart Citation