Grasping in a Cluttered Environment: Avoiding Obstacles Under Memory Guidance
Bibliographic record
Abstract
Humans often reach to remembered objects, such as when picking up a coffee cup from behind our morning paper. When reaching to previously seen, now out-of-view objects, we rely on our perceptual memory of the scene, to guide our actions (Milner & Goodale, 1995). Based in relative coordinates, encoded perceptual representations may likely exaggerate the risk associated with nearby obstacles. For instance, a cereal bowl next to our coffee cup may be judged as larger than it really is under memory-guided conditions, resulting in a more cautious obstacle avoidance approach to best prevent a messy collision. In contrast, when visual information is available up to the point when a reach is initiated, the precise positions of objects relative to the self are likely to be computed and incorporated into a motor plan, allowing for finely tuned eye-hand maneuvers around positioned obstacles. The objective of this study was to examine obstacle avoidance during memory-guided grasping. Eye-hand coordination was monitored as subjects had to reach through a pair of obstacles in order to grasp a 3D target. The availability of visual information underwent a between-subjects manipulation, such that reaches occurred either with continuous visual information (visually-guided condition), immediately in the absence of visual feedback (memory-guided no-delay condition), or after a 2-s delay in the absence of visual feedback (memory-guided delay condition). The positions and widths of obstacles were manipulated, though their inner edges remained a constant distance apart. We expected the memory-guided delay group to exhibit exaggerated avoidance strategies, particularly around wider obstacles. Results revealed subjects were able to effectively avoid obstacles in the visually-guided and memory-guided no-delay conditions, though overall performance was poorer in the no-delay group, resulting from the inability to use visual information for the online control of action. Still, subjects in these groups consistently altered the paths of the index finger and wrist and adjusted the index finger position on the target object to accommodate obstacles that obstructed the reach path to different degrees. Contrary to expectation, the memory-guided delay group resorted to a more moderate strategy, with fewer instances of altered index finger and wrist paths or adjusted index finger positions on the target object in response to positioned obstacles, though successful grasps were still seen. In other words, subjects reaching to remembered objects tended to use a “good enough” approach for avoiding obstacles. In conclusion, obstacle avoidance behaviour, driven by our stored perceptual representations of a scene, appears to adopt a more moderate, rather than exaggerative, strategy. This work was funded by Research Manitoba, NSERC CGSM, and NSERC Discovery Grant.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".