Abstract:Abstract-Human operators play a key role in robotic exploration and search missions, as the interpretation of camera images typically requires the visual perception skills of humans. Thus one the key challenges in building effective robotic systems for such missions lies in developing good operator interfaces. In this paper, we present a novel asynchronous user-guided interface for human operators of robotic search of an unknown area. Enabled by efficient methods to store and retrieve recorded images (and meta… Show more
“…However, the communication lags and limited human attention make it difficult for human operators to simultaneously inspect 4∼12 live video streams and use these to make decisions such as finding victims or directing the robots' motion. To alleviate these issues, an asynchronous interface was proposed, which shows the priority image or point of interest (POI) to the operator [21]. The experiments demonstrated that with the asynchronous interface the operator can reduce victims' marking errors [22].…”
Section: B Human-robot Interface For Spatial Searchmentioning
confidence: 99%
“…For example, in [20], [21], the robots' paths are planned by algorithms, and the images' priority is decided based on the uncovered area. In other words, the objective function of the priority images is submodular.…”
Section: B Subgoal Assistance For Human-robot Interactionmentioning
Search is an essential technology for rescue and other mobile robot applications. Many robotic search and rescue systems rely on teleoperation. One of the key problems in search tasks is how to cover the search space efficiently. Search is also central to humans' daily activities. This paper analyzes and models human search behavior using data from actual teleoperation experiments. The analysis of the experimental data uses a novel technique to decompose search data, based on structure learning and K-means clustering. The analysis explores three hypotheses: (1) humans are able to solve a complex search task by breaking it up into smaller tasks, (2) humans consider both coverage and motion cost, and (3) robots can outperform humans in search problems. The enhanced understanding of human search strategies can then be applied to the design of human-robot interfaces and search algorithms. The paper describes a technique for augmenting human search. Since the objective functions in search problems are submodular, greedy algorithms can generate near-optimal subgoals. These subgoals then can be used to guide humans in searching. Experiments showed that the humans' search performance is improved with the subgoals' assistance. INDEX TERMS Telerobotics, robot sensing systems, human-robot interaction, rescue robots, mobile robots.
“…However, the communication lags and limited human attention make it difficult for human operators to simultaneously inspect 4∼12 live video streams and use these to make decisions such as finding victims or directing the robots' motion. To alleviate these issues, an asynchronous interface was proposed, which shows the priority image or point of interest (POI) to the operator [21]. The experiments demonstrated that with the asynchronous interface the operator can reduce victims' marking errors [22].…”
Section: B Human-robot Interface For Spatial Searchmentioning
confidence: 99%
“…For example, in [20], [21], the robots' paths are planned by algorithms, and the images' priority is decided based on the uncovered area. In other words, the objective function of the priority images is submodular.…”
Section: B Subgoal Assistance For Human-robot Interactionmentioning
Search is an essential technology for rescue and other mobile robot applications. Many robotic search and rescue systems rely on teleoperation. One of the key problems in search tasks is how to cover the search space efficiently. Search is also central to humans' daily activities. This paper analyzes and models human search behavior using data from actual teleoperation experiments. The analysis of the experimental data uses a novel technique to decompose search data, based on structure learning and K-means clustering. The analysis explores three hypotheses: (1) humans are able to solve a complex search task by breaking it up into smaller tasks, (2) humans consider both coverage and motion cost, and (3) robots can outperform humans in search problems. The enhanced understanding of human search strategies can then be applied to the design of human-robot interfaces and search algorithms. The paper describes a technique for augmenting human search. Since the objective functions in search problems are submodular, greedy algorithms can generate near-optimal subgoals. These subgoals then can be used to guide humans in searching. Experiments showed that the humans' search performance is improved with the subgoals' assistance. INDEX TERMS Telerobotics, robot sensing systems, human-robot interaction, rescue robots, mobile robots.
“…This meant that an operator was still required to watch all imagery taken by all the robots. Kosti, Kaminka, and Sarne (2014) developed a novel user interface that allowed the user to view images in context of their location on the map, automatically selecting the best image showing a given location.…”
Section: The Latest Israeli Ai Achievementsmentioning
The Israeli AI CommunityIsrael is a young and a small country consisting of only approximately 20,000 square kilometers in area and a population of approximately 8 million. Since its establishment in 1948, The Israeli government has placed great importance on establishing excellent research institutions and universities.As a consequence, there are eight universities in Israel, as well as a handful of research institutions and numerous colleges, and Israel has excelled in numerous fields of research. A clear sign of this is that Israel has produced eight Nobel laureates in the past 15 years, out of 154 worldwide. Computer science research in Israel dates back to the country's founding, and five Turing Award winners (out of 62) are Israelis. AI research in Israel has been firmly established since the 1980s, and there are currently quite a few AI research groups and labs in Israeli universities.This column introduces the Israeli AI community and many of its unique attributes. It also covers a number of recent research projects in the field of AI that are done in different institutions within the country.
The Israeli Association for AIThe Israeli Association for Artificial Intelligence (IAAI), 1 a member of the European Association for Artifical Intelligence (EURAI), is an umbrella organization for AI researchers in Israel. The primary goals of the organization are to promote the study and research of AI in Israel, to encourage cooperation between Israeli AI researchers, and to promote collaboration with AI researchers worldwide.Israelis are known to be very friendly and they like to socialize. In addition, Israel's small size means that its two most distant universities -Technion in Haifa (the north) and Ben-Gurion University of the Negev (the south) -are only 187 kilometers apart. As a result, many members of IAAI have strong personal and research relations throughout the country. Very often, Israeli AI researchers from throughout the country will organize mutual visits during which they hold research meetings, give talks at seminars, or participate in M.
“…Much research has focused on improving the operator's control, suggesting various synchronous and asynchronous interfaces for operating the robots and managing the task (Wang et al 2011;Kosti, Sarne, and Kaminka 2014). Still, not all human operators possess the same level of expertise, and the effectiveness of their navigation can highly vary (McGinn, Sena, and Kelly 2017).…”
This paper proposes a heuristic algorithm for effectively summarizing the work of novice robot operators, e.g., ones recruited through crowdsourcing platforms, in search and rescue-like tasks. Such summaries can be used for many purposes, perhaps most notably for monitoring and evaluating an operator’s performance in settings where information gaps preclude automatic evaluation. The underlying idea of our method is dividing the task timeline into intervals, and extracting a subset of high-scoring and low-scoring segments within, using a heuristic scoring function. This results in a short effective summary of the operator’s work, based on which several other crowdworkers can evaluate her performance. The effectiveness of the proposed method was extensively evaluated and compared to a large set of alternative methods through a series of experiments in Amazon Mechanical Turk. The analysis of the results reveals that the proposed method outperforms all tested alternatives. Finally, we evaluate the performance one may achieve with the use of machine learning for predicting the operator’s performance in our domain. While this approach manages to reach a performance level similar to the one achieved with summaries, it requires an order-of-magnitude greater effort for training (measured in terms of crowdworkers time).
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.