Enhanced Dynamic Window Approach for socially compliant robot navigation
S. Ashwath, R. Mayank, S. Pavithra · 2026
Read Enhanced Dynamic Window Approach for socially compliant robot navigation by S. Ashwath, R. Mayank, S. Pavithra (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13186690.txt.
Description
S Ashwath, R Mayank, and S Pavithra teach a driving robot manners in a 2026 paper. A classic local planner, the Dynamic Window Approach, steers by shape and distance alone, blind to who or what blocks the way. Deep learning rivals can read a scene but cost heavy computing. The team's Semantic-DWA keeps the classic planner and adds a light layer of meaning.
A sensing step labels each blocker as a person, a pet, or an object. Hard rules then bar the robot from cutting inside set clearances for each class, such as one meter for people. In a flat test world, the classic planner crashed and broke social space rules. The new one finished every run clean, holding its distances.
Catalog record
| CREATOR | S. Ashwath, R. Mayank, S. Pavithra |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |