MPCFormer explicitly models multi-vehicle social interaction dynamics via physics-informed discrete state-space and Transformer-learned coefficients, yielding 0.86m ADE over 5s and 94.67% planning success with near-zero collisions in closed-loop tests.
Legible and proactive robot planning for prosocial human-robot interactions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2verdicts
UNVERDICTED 2representative citing papers
Proactive lane-changing at eight meters improves human ratings of robot motion in frontal hallway approaches according to a 42-participant study, with no advantage shown at intersections.
citing papers explorer
-
MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
MPCFormer explicitly models multi-vehicle social interaction dynamics via physics-informed discrete state-space and Transformer-learned coefficients, yielding 0.86m ADE over 5s and 94.67% planning success with near-zero collisions in closed-loop tests.
-
Look Further: Socially-Compliant Navigation System in Residential Buildings
Proactive lane-changing at eight meters improves human ratings of robot motion in frontal hallway approaches according to a 42-participant study, with no advantage shown at intersections.