Robot Planning in the Real World: Research Challenges and Opportunities

AI Magazine ◽  
2016 ◽  
Vol 37 (2) ◽  
pp. 76-84 ◽  
Author(s):  
Ron Alterovitz ◽  
Sven Koenig ◽  
Maxim Likhachev

Recent years have seen significant technical progress on robot planning, enabling robots to compute actions and motions to accomplish challenging tasks involving driving, flying, walking, or manipulating objects. However, robots that have been commercially deployed in the real world typically have no or minimal planning capability. These robots are often manually programmed, teleoperated, or programmed to follow simple rules. Although these robots are highly successful in their respective niches, a lack of planning capabilities limits the range of tasks for which currently deployed robots can be used. In this article, we highlight key conclusions from a workshop sponsored by the National Science Foundation in October 2013 that summarize opportunities and key challenges in robot planning and include challenge problems identified in the workshop that can help guide future research towards making robot planning more deployable in the real world.

2021 ◽  
Vol 4 (4) ◽  
pp. 10-22
Author(s):  
Patricia R. DeLucia ◽  
Amanda L. Woods ◽  
Jeong-Hee Kim ◽  
Ngan Nguyen ◽  
Eugene W. Wang ◽  
...  

This research study at a National Science Foundation Research Experience for Undergraduates site focuses on psychological research with applications to the real world. Two cohorts of undergraduates engaged in rigorous research projects on, e.g., driving, homeland security, relationships, human-computer interaction, language comprehension and production, discrimination, and health psychology. Results indicated that students and mentors perceived an improvement in the students' research skills.


2021 ◽  
Vol 14 (8) ◽  
pp. 1378-1391
Author(s):  
Surabhi Gupta ◽  
Karthik Ramachandra

Procedural extensions of SQL have been in existence for many decades now. However, little is known about their magnitude of usage and their complexity in real-world workloads. Procedural code executing in a RDBMS is known to have inefficiencies and limitations; as a result there have been several efforts to address this problem. However, the lack of understanding of their use in real workloads makes it challenging to (a) motivate new work in this area, (b) identify research challenges and opportunities, and (c) demonstrate impact of novel work. We aim to address these challenges with our work. In this paper, we present the results of our in-depth analysis of thousands of stored procedures, user-defined functions and triggers taken from several real workloads. We introduce SQL-ProcBench , a benchmark for procedural workloads in RDBMSs. SQL-ProcBench has been created using the insights derived from our analysis, and thus represents real workloads. Using SQL-ProcBench, we present an experimental evaluation on several database engines to understand and identify research challenges and opportunities. We emphasize the need to work on these interesting and relevant problems, and encourage researchers to contribute to this area.


Author(s):  
Heidi Agerbo

AbstractThough a vast amount of dictionary analyses have been produced over the years, hardly any of these have mentioned the operative function, which has been overlooked in most lexicographical literature. With short analyses of 12 existing dictionaries ranging from the 18th century to the 21st century, this article shows that many dictionaries have indeed been produced to satisfy operative needs. Based on this result, it is clear that the operative function deserves a place in lexicographical theory. An interesting finding that came out of these analyses was that especially dictionaries from the 18th to the early 20th centuries (the old dictionaries) were written to accommodate several types of information needs that their users would come across in the real world, including operative needs, whereas the focus of most contemporary dictionaries is to satisfy linguistic information needs. This is an interesting change in focus, which this article criticises. Based on the above mentioned analyses, a number of questions are raised to guide future research into the operative function.


2019 ◽  
Vol 9 (8) ◽  
pp. 1744-1768 ◽  
Author(s):  
Muhammad Haris Mahyuddin ◽  
Yoshihito Shiota ◽  
Kazunari Yoshizawa

A review of the recent progress in revealing the structures, formation, and reactivity of the active sites in Fe-, Co-, Ni- and Cu-exchanged zeolites as well as outlooks on future research challenges and opportunities is presented.


In 1965 several anthropologists drew up plans for a one-year pilot study of the archeology and ethnohistory of the Wichita Indian tribes. After financial support had been generously provided by the National Science Foundation, the proposed research was carried out. This is a report on the results of that study. The pilot study was designed to: a) obtain a body of field data from the components of the Spanish Fort sites, the largest and best=documented of the historic Wichita sites in the Red River area; b) make test excavations at several other sites in order that a problem=oriented program of future research can be accurately planned; c) attempt to locate, by field reconnaissance, sites that relate to the Wichita occupation of the southern plains on both the historic and prehistoric time levels; d) make a survey of available ethnohistorical data in order (1) to compile a bibliography of documentary materials relevant to Wichita ethnohistory, (2) to make a detailed study of documents that relate specifically to the excavations being carried out at Spanish Fort and at the sites being tested, (3) to seek information that might lead to the field locations of other Wichita sites, and (4) to appraise those sources best suited for more extended examination. The co-investigators of the project were Tyler Bastian of the Museum of the Great Plains, Robert E. Bell of The University of Oklahoma, Edward B. Jelks of Southern Methodist University, and W.W. Newcomb of the Texas Memorial Museum at The University of Texas. Bastian supervised the archeological field work in Oklahoma under the direction of Bell. Jelks directed the archeological work in Texas. Newcomb directed the ethnohistorical research. Marvin E. Tong of the Museum of the Great Plains served the project as general coordinator. The main part of the ethnohistorical study consisted of a thorough search of the archives at The University of Texas for documents relating to Wichita ethnohistory. The archeological work included extensive excavations at the Longest Site in Oklahoma and at the Upper Tucker and Coyote Sites in Texas. More limited excavations were carried out at the Glass and Gas Plant Sites in Texas. Several other archeological sites were visited but not excavated beyond a test pit or two: the Devils Canyon and Wilson Springs Sites in Oklahoma, and the Gilbert, Stone, Vinson, and Womack Sites in Texas. An effort was also made to locate several sites in Oklahoma and Texas which were reported in historical documents but which had not been located in the field. After the library research and the archeological field work had been completed, a brief, general report could have been prepared to satisfy our contractual obligation to the National Science Foundation. It was felt, however, that the data which had been collected would be of interest to archeologists and ethnohistorians and, if possible, it should be made available to them in some detail without delay. Consequently, a series of descriptive papers was prepared instead of a summary report. Those papers are presented here.


Author(s):  
Lincy Mathews ◽  
Seetha Hari

A very challenging issue in real world data is that in many domains like medicine, finance, marketing, web, telecommunication, management etc., the distribution of data among classes is inherently imbalanced. A widely accepted researched issue is that the traditional classifier algorithms assume a balanced distribution among the classes. Data imbalance is evident when the number of instances representing the class of concern is much lesser than other classes. Hence, the classifiers tend to bias towards the well-represented class. This leads to a higher misclassification rate among the lesser represented class. Hence, there is a need of efficient learners to classify imbalanced data. This chapter aims to address the need, challenges, existing methods and evaluation metrics identified when learning from imbalanced data sets. Future research challenges and directions are highlighted.


Author(s):  
Mary K. Stewart ◽  
Danielle E. Hagood ◽  
Cynthia Carter Ching

It is rare for research on augmented-reality games to examine equity and access as grounded in features of the actual neighborhoods where game play takes place, and in the affordances of communities and their built environments for gamified ambulatory physical activity in the real world. This chapter studies two diverse groups of middle-school youth, situated in urban and suburban areas, who wore activity monitors as they went through daily activities and played an online game that synced with their monitors. The game drew data from the wearable devices so that the more youth engaged in step-countable physical activity in the real world, the more game-world energy they earned. This chapter analyzes the actual communities where our participants' activity and game play was situated. The chapter lays out the multi-modal data sources in that analysis and provides some potential models that can be employed by others in related work. Finally, the chapter closes by articulating some directions and concerns for future research in a gamified physical world.


2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e16249-e16249
Author(s):  
Salwan Al Mutar ◽  
Muhammad Shaalan Beg ◽  
Eric Hansen ◽  
Andrew J. Belli ◽  
Maegan Vaz ◽  
...  

e16249 Background: The difference between the FOLFIRINOX and gemcitabine/nab-paclitaxel (GnP) regimens’ clinical trial designs limit the ability to generate cross-study comparisons. Therefore, there is a significant need to understand the impact of various demographic and clinical characteristics on the effectiveness of these systemic therapies in the real-world treatment setting. This study seeks to compare the real-world outcomes of patients with metastatic pancreatic cancer treated with frontline FOLFIRINOX or GnP. Methods: Patients with primary metastatic pancreatic cancer who received first-line (1L) FOLFIRINOX or GnP were identified in the COTA real-world database. The COTA database is a de-identified database of real-world data (RWD) derived from the electronic health records of healthcare providers in the United States. Real-world overall response rate (rwORR) was calculated as the proportion of patients achieving complete response (CR) or partial response (PR). Overall survival (OS) was calculated using the Kaplan-Meier method and multivariate analyses utilized Cox proportional hazards. Results: The overall qualified cohort (n=236) was stratified by 1L FOLFIRINOX (n=109) or GnP (n=127). Select patient characteristics are shown in table. Patients treated with 1L FOLFIRINOX showed greater rwORR as compared to those treated with GnP (68.8% vs. 55.9%, p=0.04). Additionally, patients treated with 1L FOLFIRINOX had longer median OS (14.4 vs 11.4 mos, respectively). In univariate analysis, patients treated with GnP had a greater chance of mortality (HR: 1.3, 95% CI: 1.0, 1.8, p=0.05). This relationship strengthened in multivariate analysis (GnP treated HR: 1.6, 95% CI: 1.1, 2.1, p=0.01). Conclusions: Due to lack of enrollment of representative patients in clinical trials and in the absence of a comparative clinical trial, real-world experience with chemotherapy regimens provide critical insights on the outcome of treatments. In our cohort, patients treated with frontline GnP had a significantly greater chance of mortality as compared to patients treated with frontline FOLFIRINOX. The FOLFIRINOX cohort also showed greater rwORR. Future research will continue to expand on treatment patterns in subsequent lines of therapy, as well as emerging therapy types, in order to better understand the optimal treatment sequence in metastatic pancreatic cancer.[Table: see text]


Sign in / Sign up

Export Citation Format

Share Document