Table 1

Comparison of LPPF with existing end-to-end systems.

Feature LPPF (proposed) Depth-to-Costmap RL World-model planners Learning-based local planners
Latency-aware gradient gating Yes No No No
Depth-confidence dynamic cost coupling Yes Partial No No
Layer-wise quantization strategy Yes No No No
Real-time constraint (≤50 ms) Yes Variable Variable Variable

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.