scholarly journals Mixed-initiative Variable Autonomy for Remotely Operated Mobile Robots

2021 ◽  
Vol 10 (4) ◽  
pp. 1-34
Author(s):  
Manolis Chiou ◽  
Nick Hawes ◽  
Rustam Stolkin
Keyword(s):  
Mobile Robots ◽  
Disaster Response ◽  
Context Aware ◽  
Test Arena ◽  
Secondary Tasks ◽  
Real Robot ◽  
Improved Performance ◽  
Mixed Initiative ◽  
Operator Workload ◽  
Different Levels

This article presents an Expert-guided Mixed-initiative Control Switcher (EMICS) for remotely operated mobile robots. The EMICS enables switching between different levels of autonomy during task execution initiated by either the human operator and/or the EMICS. The EMICS is evaluated in two disaster-response-inspired experiments, one with a simulated robot and test arena, and one with a real robot in a realistic environment. Analyses from the two experiments provide evidence that: (a) Human-Initiative (HI) systems outperform systems with single modes of operation, such as pure teleoperation, in navigation tasks; (b) in the context of the simulated robot experiment, Mixed-initiative (MI) systems provide improved performance in navigation tasks, improved operator performance in cognitive demanding secondary tasks, and improved operator workload compared to HI. Last, our experiment on a physical robot provides empirical evidence that identify two major challenges for MI control: (a) the design of context-aware MI control systems; and (b) the conflict for control between the robot’s MI control system and the operator. Insights regarding these challenges are discussed and ways to tackle them are proposed.

scholarly journals 132 Performance response of the grow-finish pig (38 to 142 kg) fed different levels of tryptophan:lysine in diets containing 40% dry distiller grains with solubles

2020 ◽  
Vol 98 (Supplement_4) ◽  
pp. 110-111
Author(s):  
David A Clizer ◽  
Paul Cline ◽  
Brent Frederick ◽  
Ryan S Samuel
Keyword(s):  
South Dakota ◽  
Soybean Meal ◽  
Carcass Weight ◽  
State University ◽  
Research Facility ◽  
Performance Response ◽  
Improved Performance ◽  
Dietary Treatments ◽  
Swine Diets ◽  
Different Levels

Abstract Dried distiller grains with solubles (DDGS) is a popular protein source in grow-finish swine diets to replace soybean meal. An experiment was conducted at the South Dakota State University commercial swine research facility to determine the effect of standardized ileal digestible (SID) Trp:Lys ratio in grow-finish swine diets containing 40% DDGS compared to a standard corn-soybean meal diet. A total of 1,170 pigs (38.6 ± 0.2 kg initial BW) were utilized in a 98-d trial (9 pens per treatment). Pens of pigs were randomly allotted to 1 of 4 DDGS dietary treatments providing SID Trp at 15, 18, 21, and 24% of Lys or a corn-soybean meal diet (18%). Diets were isocaloric, with lysine at 100% of the requirement. From d 0 to 82, increasing Trp:Lys ratio in DDGS diets improved (P < 0.01) BW, ADG, and ADFI with no effect on F:G. Pigs fed the corn-soybean meal diet had greater (P < 0.01) BW, ADG, ADFI, and F:G compared to the DDGS diets with the exception of the ADFI of the 24% Trp:Lys treatment. From d 82 to 98, increasing SID Trp:Lys in DDGS diets had no effect on performance. Overall (d 0 to 98), increasing SID Trp:Lys in DDGS diets increased (P < 0.02) final BW and ADG, but pigs failed to perform to the same degree as the corn-soybean meal diet. Increasing SID Trp:Lys in DDGS diets resulted in an increase in hot carcass weight (P < 0.01); however, diets containing DDGS had decreased (P < 0.02) hot carcass weight, dressing percentage, percent lean, and loin depth compared to pigs fed the corn-soybean meal diet. These results indicate that increasing the SID Trp:Lys in diets containing 40% DDGS improved performance in early grow-finish phases with no effect in late finishing, but performance was inferior to standard corn-soybean meal diets.

The Effects of Certain Gimbal Orders and Workloads on Target Acquisition

1974 ◽  
Vol 18 (2) ◽  
pp. 153-157
Author(s):  
Dennis L. Price
Keyword(s):  
Target Detection ◽  
Identification Performance ◽  
Target Task ◽  
Terrain Model ◽  
Spare Time ◽  
Word Task ◽  
Heavy Workload ◽  
Improved Performance ◽  
Imaging Sensors ◽  
Operator Workload

If air-to-ground imaging sensors are mounted to aircraft by different gimbal order systems, the scenery at the displays will rotate differently, even though the flight paths are identical. Eighteen experienced pilots were tested to investigate the effects such scene motions might have on target detection, recognition, and identification performance, and also on operator workload. The Martin Marietta 600:1 scale terrain model was used to provide the imagery of three gimbal orders: roll-pitch, yaw-pitch, and pitch-yaw. Target runs simulated started at 20k ft. slant range, and maintained a 4k ft. altitude, and 2500 or 5000 feet offset. They were 30-second runs at a speed of 350 knots. The pitch-yaw gimbal order was associated with the greatest range-to-target scores and the lightest workloads. Also, the workload measured for each gimbal order and the workload measured for a word task from the Montana Meaningfulness Scale were added together for each subject. The sum was the estimated workload for that subject for the combined tasks, which were presented on two monitors. The six subjects with the heaviest workload estimates and the six with the lightest were compared on range-to-target scores. The heavy workload group demonstrated a trend effect for improved performance compared to the light workload group, p < .01. However, significant degraded performance occurred when the results of all subjects for this words and target task were compared with similar trials in which the second display was monitored during the observer's spare time only.

Measurement of Workload by Secondary Tasks

1979 ◽  
Vol 21 (5) ◽  
pp. 529-548 ◽  
Author(s):  
George D. Ogden ◽  
Jerrold M. Levine ◽  
Ellen J. Eisner
Keyword(s):  
Reaction Time ◽  
Literature Review ◽  
Choice Reaction Time ◽  
Future Research ◽  
Secondary Tasks ◽  
Memory Monitoring ◽  
Operator Workload

The post-1965 literature on the use of secondary tasks in the assessment of operator workload was surveyed. Twelve classes of tasks were identified; the most frequently used were choice reaction time, memory, monitoring, and tracking. The literature review did not suggest a single best task or class of tasks for the measurement of workload. Limitations in using secondary tasks are discussed, and directions for future research are presented.

Effects of Distraction in On-Road Level 2 Automated Driving: Impacts on Glance Behavior and Takeover Performance

2020 ◽  
pp. 001872082093679
Author(s):  
Shiyan Yang ◽  
Jonny Kuo ◽  
Michael G. Lenné
Keyword(s):  
Automated Driving ◽  
Test Drive ◽  
Secondary Tasks ◽  
Music Selection ◽  
Driver Monitoring ◽  
Monitoring Technologies ◽  
And Behavior ◽  
The Impact ◽  
Level 2 ◽  
Different Levels

Objective The paper aimed to investigate glance behaviors under different levels of distraction in automated driving (AD) and understand the impact of distraction levels on driver takeover performance. Background Driver distraction detrimentally affects takeover performance. Glance-based distraction measurement could be a promising method to remind drivers to maintain enough attentiveness before the takeover request in partially AD. Method Thirty-six participants were recruited to drive a Tesla Model S in manual and Autopilot modes on a test track while engaging in secondary tasks, including temperature-control, email-sorting, and music-selection, to impose low and high distractions. During the test drive, participants needed to quickly change the lane as if avoiding an immediate road hazard if they heard an unexpected takeover request (an auditory warning). Driver state and behavior over the test drive were recorded in real time by a driver monitoring system and several other sensors installed in the Tesla vehicle. Results The distribution of off-road glance duration was heavily skewed (with a long tail) by high distractions, with extreme glance duration more than 30 s. Moreover, being eyes-off-road before takeover could cause more delay in the urgent takeover reaction compared to being hands-off-wheel. Conclusion The study measured off-road glance duration under different levels of distraction and demonstrated the impacts of being eyes-off-road and hands-off-wheel on the following takeover performance. Application The findings provide new insights about engagement in Level 2 AD and are useful for the design of driver monitoring technologies for distraction management.

Trust-based mixed-initiative teleoperation of mobile robots

2016 ◽  
Author(s):  
H. Saeidi ◽  
F. McLane ◽  
B. Sadrfaidpour ◽  
E. Sand ◽  
S. Fu ◽  
...  
Keyword(s):  
Mobile Robots ◽  
Mixed Initiative

Building Context-Aware E-Commerce Systems

2010 ◽  
pp. 1021-1029
Author(s):  
Anahit Martirosyan ◽  
Thomas Tran ◽  
Azzedine Boukerche
Keyword(s):  
Data Mining ◽  
Social Networks ◽  
Context Aware ◽  
Work Context ◽  
Privacy Issue ◽  
Data Mining Techniques ◽  
Proposed Model ◽  
Use Context ◽  
Using Data ◽  
Different Levels

Context is any information/knowledge about an application and user that can be used by an e-commerce system to provide efficient services to the users of the system. In this article, we propose to extend usage of context as compared to previously designed context-aware e-commerce systems. While in previous work, context was mainly considered for mobile e-commerce systems, we propose to build and use context for e-commerce systems in general. The context is employed to tailor an e-commerce application to the preferences and needs of users and provide insights into purchasing activities of users and particular e-commerce stores by means of using Data Mining techniques. This article proposes a model of context that includes micro-, macro- and domain contexts that constitute knowledge about the application and its user on different levels of granularity. The article also proposes a technique for extracting groups in social networks. This knowledge is part of macro-context in the proposed model of context. Moreover, the article discusses some of the challenges of incorporating context with e-commerce systems, emphasizing on the privacy issue, with an ultimate goal of developing intelligent e-commerce systems.

Self-Partitioning State Space for Behavior Acquisition of Vision-Based Mobile Robots

2001 ◽  
Vol 13 (6) ◽  
pp. 625-636 ◽  
Author(s):  
Takayuki Nakamura ◽  
◽  
Tsukasa Ogasawara
Keyword(s):  
Computer Simulation ◽  
Reinforcement Learning ◽  
Mobile Robots ◽  
State Space ◽  
Experimental Results ◽  
Generalization Capability ◽  
Soccer Robot ◽  
Generalization Problem ◽  
Real Robot ◽  
Robot Tasks

An input generalization problem is one of the most important in applying reinforcement learning to real robot tasks. To cope with this problem, we propose a self-partitioning state space algorithm, which can make nonuniform quantization of state space. To show that our algorithm has generalization capability, we apply our method to two tasks in which a soccer robot shoots a ball into a goal and prevent a ball from entering a goal. To show the validity of this method, the experimental results for computer simulation and a real robot are shown.

Sign in / Sign up

Export Citation Format

Share Document