Diminished reality is an immersive technology that can selectively reduce the visual salience of real-world objects, altering how people see their environment without physically changing it. This makes it a novel and innovative form of digital choice architecture in supporting consumer decision-making. While the technical development of diminished reality has advanced within computer science, our study is the first to examine how people experience and interact with the technology in practice and reflect its use from a behavioral science perspective. This study addresses these gaps by exploring how diminished reality shaped food-related decisions and how consumers envisioned its future adoption. To explore this, we developed a diminished reality prototype designed to support sustainable food choices and used it to conduct a qualitative study combining think-aloud protocols and semi-structured interviews with 25 participants in a simulated supermarket setting. Using framework method analysis, we found that diminished reality shaped participants’ choices by guiding attentional processes, altering perceptions of product presence, sparking curiosity, and prompting moral reasoning – all of which interacted with habitual preferences to shape decision-making. We also explored key motivations and barriers related to future adoption of diminished reality, including perceived ease of use, usefulness, autonomy, psychological reactance and trust in technology. These findings contribute to the emerging literature on mixed reality and digital choice architecture, offering theoretical insights into consumer decision-making and practical implications for future diminished reality development and implementation.

Performing unstructured grasping tasks in cluttered or obstacle-rich food processing environments is a key challenge in robotic systems. This work presents a task-adaptive grasping approach for a dual-arm anthropomorphic robot, named Herdsman, developed for the food industry. With an articulated torso, Herdsman is able to perform human-like reaching motions for more flexible grasping operations. To recognize the target object and extract the features for grasping, a vision pipeline, including a lightweight network GDC-YOLO for real-time object detection and a U-ReSENet network for grasping detection enhancement, is designed based on convolutional neural networks. After the detection comes the grasp execution, where a task-adaptive grasping strategy that works with the articulated torso is put forward to carry out grasping tasks in unstructured environments. Comparative experiments are designed to evaluate the detection performance between the proposed network and other popular networks for object detection and grasping detection. In addition, the task-adaptive grasp strategy for the Herdsman robot is experimentally validated by grasping the objects at different heights. The results have shown that the task-adaptive grasping solution exhibits robustness against variations in the target object position, which could be a promising approach for its application in unstructured environments requiring autonomous grasping.