Bibliographic record
Abstract
This thesis examines the problem of actively searching for an object in a 3D environment, subject to a cost constraint. The thesis shows that different variants of this problem are NP-Hard. The tradeoffs of localizing vs. detecting a target object, using single-view and multiple-view recognition, under imperfect dead-reckoning, and an imperfect recognition algorithm are explored. The effects that finite computational resources, input noise, occlusion, and the related object representation class complexities have in terms of localizing all objects present in the search region are investigated. Various bounds relating the feature detection noise-rate to the Vapnik-Chervonenkis-dimension of an object representable by an architecture satisfying the given computational constraints are presented. These prove that under certain conditions, the corresponding classes of object localization and recognition problems are efficiently learnable in the presence of noise and under a purposive learning strategy. Under this formulation, the existence of a number of emergent relations are proven, which demonstrate that selective attention is not only necessary due to computational complexity constraints, but it is also necessary as a noise-suppression mechanism and as a mechanism for efficient object class learning. An implementation of an active 3D object localization system on a state-of-the-art visually guided humanoid robot is presented. This involves a target probability updating scheme providing an efficient solution to the best next viewpoint selection problem. It employs a recognition architecture, for attending to the view-tuned units at the proper intrinsic scales and for purposively controlling the sensor's coordinate frame, giving control of the extrinsic image scale and achieving the proper sequence of informative views of the scene. This demonstrates the feasibility of using state of the art vision-based systems for efficient and reliable object localization in an indoor 3D environment. The thesis concludes by demonstrating that under certain conditions, the effects of dead-reckoning errors can be effectively addressed by a visually-guided agent. It is argued that reliable vision systems that are non-camera specific must purposively control all sensor parameters. This suggests ways of improving the evaluation techniques of vision algorithms and motivates topics for future research.
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.
How this classification was reachedexpand
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".