Chronic stress and anxiety severely affect breast cancer survivors’ (BCSs) mental health and well-being. Peer support has been shown to enhance psychological empowerment, while biofeedback offers a promising approach to improve physiological relaxation through self-regulation. However, few studies explored combining both for BCSs. We conducted a formative study with clinicians and BCSs to identify requirements and preferences for VR biofeedback. Informed by the findings, we proposed a VR-based dyadic biofeedback system, Cobreath, which integrates breathing and heart rate variability (HRV) feedback into a calming virtual environment, allowing two users to practice breathing-focused relaxation simultaneously. Through a clinical user study with ten clinicians and a between-subjects study with 32 BCSs, we demonstrated that Cobreath’s dyadic mode improved biofeedback effectiveness and provided a better user experience compared to the individual mode. We further discuss insights and design considerations for developing dyadic VR-biofeedback applications to support the mental well-being of BCSs and potential applications.

One of the unresolved challenges for autonomous vehicles is occlusion-aware decision-making under the high uncertainty of various occlusions. Recent occlusion-aware decision-making methods encounter issues such as overly conservative behavior, high computational complexity, or scenario scalability challenges. Benefiting from automatically generating data by exploration randomization, we uncover that reinforcement learning (RL) may show promise in occlusion-aware decision-making. However, previous occlusion-aware RL faces challenges in expanding to various dynamic and static occlusion scenarios, low learning efficiency, and lack of predictive ability. To address these issues, we introduce Pad-AI, a self-reinforcing framework to learn occlusion-aware decision-making through active perception. Pad-AI utilizes vectorized representation to represent occluded environments efficiently and learns over the semantic motion primitives to focus on high-level active perception exploration. Furthermore, Pad-AI integrates prediction and RL within a unified framework to provide risk-aware learning and reliable policy optimization. Our framework was tested in challenging scenarios under both dynamic and static occlusions and demonstrated efficient perception-aware exploration performance to other strong baselines in closed-loop evaluations.

Food intake monitoring can play an important role in the prevention of malnutrition in the aging population, but traditional tools may not be adequate for use in this target group. These tools typically involve the use of questionnaires or food diaries that require manual data entry. Due to their time-consuming nature, they are often incomplete, contain mistakes, or not used at all. An alternative to self-reporting tools, in the form of a plate system that automatically measures the consumed food during the meal, is presented in this paper. Furthermore, the system can estimate the location where each bite was taken on the plate. The system is compatible with an off-the-shelf plate that is mounted on top of a base station. Weight sensors are integrated in the base, allowing for easy removal and cleaning of the plate. Localization of bites is done by looking at the movement of the center of mass during eating. When used with a compartmentalized plate, the amount of consumed food per compartment can be measured. With prior knowledge of the type of food in each compartment, this can give an indication of calories and nutritional intake. We present a bite detection algorithm using a random forest decision tree classifier. Data from 24 aging adults (ages 52-95) eating a single meal with chopsticks was used to train and evaluate the model. Out of a total of 836 true annotated bites, the algorithm detected 602 with a precision and recall of 0.78 and 0.76, respectively. By summing the weights of detected bites from each compartment, the algorithm was able to estimate the amount of food taken per compartment with an average error of (8 ±8)% of the portion size.

Effective stroke rehabilitation typically involves improving both motor function and mental state. Traditional rehabilitation systems are generally expensive, not portable and difficult to operate. As a first step toward overcoming these existing shortcomings, we developed a cellphone augmented reality (AR) rehabilitation system for stroke rehabilitation. Three serious games for upper limb motor function and cognitive training were developed in which patients move their arms to touch virtual targets generated in the three-dimensional AR environment. Patients received visual and vibration feedback after successfully touching each target. Eight stroke patients with upper limb dysfunction performed pilot validation testing with the cellphone AR system. Motor function performance was evaluated based on performance in the AR games and mental state was evaluated via questionnaires self-reporting various aspects of mental state. Results showed that motor performance improved by the last trial as compared to the first trial (p<;0.05). In addition, the majority of patients reported that they felt `relaxed' and `happy' while playing the AR rehabilitation games. These results demonstrate the potential of cellphone AR rehabilitation to improve upper-limb motor function and mental state for stroke patients and lay a foundation for a future home-based rehabilitation paradigm.