An Introspective Learning Algorithm that Achieves Robust Adaptive Control of a Quadrotor Helicopter
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.
Bibliographic record
Abstract
This paper looks at applying a novel robust adaptive control algorithm to achieve stable adaptive control of a quadrotor helicopter. In direct adaptive control, drift of adaptive parameters to large magnitudes can lead to control signal chatter and bursting behavior. Drift is likely to happen when systems are affected by disturbances, for quadrotor helicopters when picking up payloads or flying in windy conditions. Traditional methods to stop weight drift rely on simple mathematical modifications of the parameter/weight update laws, by limiting or halting weight updates in a simplistic fashion. However, performance may be limitedfor a quadrotor helicopter flying in windy conditions performance may be far from adequate. This paper proposes a design of an algorithm to supervise weight updates in a direct adaptive control scheme when using the Cerebellar Model Arithmetic Computer (CMAC) as the nonlinear approximator. The new algorithm makes an introspective decision on when to halt weight updates, based on the perceived affect of each weight update on the error within the local domain of each CMAC basis function. In fact, each domain casts a weighted vote as to whether it perceives a beneficial effect from the weight update. An addition of the weighted votes determines whether the update will be kept in permanent memory or not. Simulation results with a quadrotor helicopter show this novel approach can halt weight drift, achieving both high performance and stability, in the case of uncertain payload and large unmeasured sinusoidal disturbance a situation where the common e-modification robust adaptive weight update cannot achieve a practical result.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it