Teamwork is best achieved when members of the team understand one another. Human–robot collaboration poses a particular challenge to this goal due to the differences between individual team members, both mentally/computationally and physically. One way in which this challenge can be addressed is by developing explicit models of human teammates. Here, we discuss, compare and contrast the many techniques available for modeling human cognition and behavior, and evaluate their benefits and drawbacks in the context of human–robot collaboration.
BackgroundThe primary aim of this study was to assess the level of engagement in computer-based simulations of functional tasks, using a haptic device for people with chronic traumatic brain injury. The objectives were to design functional tasks using force feedback device and determine if it could measure motor performance improvement.MethodsA prospective crosssectional study was performed in a biomedical research facility. The testing environment consisted of a single, interactive, stylus-driven computer session navigating virtual scenes in 3D space. Subjects had a haptic training session (TRAIN) and then had three chances to perform each virtual task: (i) remove tools from a workbench (TOOL), (ii) compose 3 letter words (SPELL), (iii) manipulate utensils to prepare a sandwich (SAND), and (iv) tool use (TUSE). Main Outcome Measures included self-report of engagement in the activities, improved performance on simulated tasks and observer estimate as measured by time to completion or number of words completed from baseline, correlations among performance measures and self-reports of boredom, neuropsychological symptom inventory (NSI), and The Purdue Peg Motor Test (PPT).ResultsParticipants were 19 adults from the community with a 1 year history of non-penetrating traumatic brain injury (TBI) and were able to use computers. Seven had mild, 3 moderate and 9 severe TBIs. Mean score on the Boredom Proneness Scale (BPS): 107 (normal range 81–117); mean NSI:32; mean PPT 54 (normal range for assembly line workers >67). Responses to intervention: 3 (15%)subjects did not repeat all three trials of the tasks; 100% reported they were highly engaged in the interactions; 6 (30%) reported they had a high level of frustration with the tasks, but completed them with short breaks. Performance measures: Comparison of baseline to post training: TOOL time decreased by (mean) 60 sec; SPELL increased by 2.7 words; TUSE time decreased by (mean) 68 sec; and SAND time decreased by (mean) 72 sec. PPT correlated with TOOL (r=−0.65, p=0.016) and TUSE time (r=−0.6, p=0.014). SPELL correlated with Boredom score (r=0.41, p=0.08) and NSI (r=−.49, p=0.05).ConclusionPeople with chronic TBI of various ages and severity report being engaged in using haptic devices that interact with 3D virtual environments. Haptic devices are able to capture objective data that provide useful information about fine motor and cognitive performance.
This is a study on the development of a road following vision-based guidance system for unmanned air vehicles (UAV) in real world applications. Currently, autonomous navigation requires the use of GPS. In many applications, however, dependence on GPS is undesirable. GPS signals are weak and can be jammed easily. Also, GPS waypoints may not be up-to-date. In recent years, vision-based navigation has been gaining popularity. Vision-based guidance requires existence of visible paths or extended landmarks for air vehicles to detect and follow. Roads are the most commonly available path to follow. Moreover, the abundance of events that happen along roads make them appealing subjects of surveillance. Many road detection (single images) and road tracking (videos) algorithms have been proposed in the literature. Fast detection and tracking has been the emphasis of those intended for UAVs. Due to the complexity of road detection, we not only need advanced software but also the most effective sensors. In this paper, we propose a road following algorithm that uses both RGB camera and hyperspectral sensor and report the results of actual test flights conducted in different locations and different seasons.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.