Being able to explore an environment and understand the location and type of all objects therein is important for indoor robotic platforms that must interact closely with humans. However, it is difficult to evaluate progress in this area due to a lack of standardized testing which is limited due to the need for active robot agency and perfect object ground-truth. To help provide a standard for testing scene understanding systems, we present a new robot vision scene understanding challenge using simulation to enable repeatable experiments with active robot agency. We provide two challenging task types, three difficulty levels, five simulated environments and a new evaluation measure for evaluating 3D cuboid object maps. Our aim is to drive state-of-the-art research in scene understanding through enabling evaluation and comparison of active robotic vision systems.

Background: Numerous factors influence patient recruitment to, and retention on, peritoneal dialysis (PD), but a major challenge is a perceived “inaccessibility” to treating clinicians. It has been suggested that remote patient monitoring (RPM) could be a means of improving such oversight and, thereby, uptake of PD. Objective: To describe patient and clinician perspectives toward RPM and the use of applications (Apps) suitable for mobiles, tablets, or computers to support the provision of PD care. Design: Qualitative design using semi-structured interviews. Setting: All patient participants perform PD treatment at home under the oversight of an urban PD unit in Sydney, Australia. Patient and clinician interviews were conducted within the PD unit. Participants: 14 participants (5 clinicians [2 nephrologists, 3 PD nurses] and 9 patients treated with PD). Methods: Semi-structured interviews were conducted using interview guides tailored for clinician and patient participants. Transcripts were coded and analyzed by a single researcher using thematic analysis. Results: Six themes were identified: perceived benefits of RPM implementation (offering convenience and efficiency, patient assurance through increased surveillance, more complete data and monitoring adherence), uncertainty regarding data governance (protection of personal data, data reliability), reduced patient engagement (transfer of responsibility leading to complacency), changing patient-clinician relationships (reduced patient-initiated communication, the need to maintain patient independence), increased patient and clinician burden (inadequate technological literacy, overmanagement leading to frequent treatment changes), and clinician preference influencing patient behavior. Limitations: The interviews were conducted in English only and with participants from a single urban dialysis unit, which may limit generalizability. Conclusions: For patients and clinicians, advantages from the use of RPM in PD may include increased patient confidence and assurance, improved treatment oversight, more complete data capture, and overcoming barriers to data documentation. Careful patient selection and patient and clinician education may help to optimize the benefits of RPM, maintain patient independence, and reduce the risks of patient disengagement. The use of an App may support RPM; however, participants expressed concerns about increasing the burden on some patients through the use of unfamiliar technology. Human Research Ethics Committee Approval Number: CH62/6/2019-028