Safe Navigation via Integrated Perception and Control
Cong Li, Yongchao Wang, Fangzhou Liu, Xinglong Zhang · 2025
Constraint learning for safe Operation in unforeseen regions is discussed in Chapter 4 . The preceding approaches follow a common mapping, planning, and control decoupled approach to complete safe execution under uncertainties. Alternatively, this chapter integrates perception with control levels to build safe learning systems resilient to unforeseen environments. This is achieved by the control-level quadratic optimization with the constraints, referred to as instantaneous local control barrier functions and goal-driven control Lyapunov functions, learned from perceptional signals.