MétaCan
Menu
Back to cohort
Record W2324668475 · doi:10.2514/6.2016-1667

Hard Real-Time General-Purpose Robotic Simulations of Autonomous Air Vehicles

2016· article· en· W2324668475 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueAIAA Modeling and Simulation Technologies Conference · 2016
Typearticle
Languageen
FieldComputer Science
TopicReal-Time Systems Scheduling
Canadian institutionsYork University
Fundersnot available
KeywordsComputer scienceRobotReal-time computingAeronauticsArtificial intelligenceEngineering

Abstract

fetched live from OpenAlex

High-fidelity general-purpose robotic simulators are a special class of simulator designed to simulate all the components of a real-world robotics system, including autonomous air vehicles and planetary exploration rovers, so that a real-world system can be tested and verified before/during deployment on the real-world hardware. General-purpose robotic simulators can simulate sensors, actuators, obstacles, terrains, environments, physics, lighting, fluids, and air particles, while also providing a means to verify the system’s autonomous algorithms by using the simulated vehicle in place of the real-world one. General-purpose robotic simulators are typically coupled with an abstract robotic control interface so that autonomous systems evaluated on the simulated vehicles can be deployed, unchanged, on the corresponding real-world vehicles and vice versa. However, the problem with the current technology and research is that neither the robotic simulators nor the robotic control interfaces support Hard Real-Time capabilities, and cannot guarantee that Hard Real-Time constraints will be met. The lack of Hard Real-Time support has major implications on both the utility and the validity of the simulation results and the functioning of the realworld autonomous vehicle. As a solution, this paper will present Hard-RTSim, a novel hard real-time simulation framework that will: 1) Bring Hard Real-Time support to generalpurpose robotic simulators; and 2) Bring Hard Real-Time support to abstract robotic control interfaces. Hard-RTSim guarantees that simulated events in the environment or modeled vehicle are produced and handled with finite (bounded) accuracy and precision. Furthermore it improves these temporal responses to ensure these bounds are representative of temporal requirements for a wide range of scenarios. The Hard-RTSim framework ensures that the simulator and the hard real-time processes will actually get to use the CPU when they request/need it, no matter how many other processes are loaded on the CPU. The experimental results of using the Hard-RTSim framework compared to not using it yield a huge improvement in responsiveness and reliability. There is an improvement of 35% when the CPU is minimally loaded and then as the CPU load is increased the improvement increases as well, all the way up to a 98% improvement when the CPU is loaded at its maximum. These substantial improvements in precision and reliability will help to further the state of space exploration, aerospace technology, and produce better and more reliable autonomous aerial vehicles and planetary exploration rovers.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.500
Threshold uncertainty score0.720

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.037
GPT teacher head0.262
Teacher spread0.225 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it