# HALO: Hazard-Aware Landing Optimization for Autonomous Systems

**Authors:** Christopher R. Hayner, Samuel C. Buckner, Daniel Broyles, Evelyn Madewell, Karen Leung, Behcet Acikmese  
**arXiv:** [2304.01583](https://arxiv.org/abs/2304.01583)  
**Date:** 2023-04-04  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2304.01583v1/

## Key points

- Autonomous aerial vehicles require the ability to identify and reason about potentially hazardous landing sites
- A coupled perception-planning solution called HALO (Hazard-Aware Landing Optimization) is presented
- HALO combines two novel algorithms: Hazard-Aware Landing Site Selection (HALSS) and Adaptive Deferred-Decision Trajectory Optimization (Adaptive-DDTO)
- HALSS processes point cloud information to identify feasible safe landing zones
- Adaptive-DDTO is a multi-target contingency planner that adaptively replans as new perception information is received
- The approach achieves greater landing success while being more fuel-efficient compared to a non-adaptive DDTO approach in a simulated Martian environment
- HALO is a promising solution for future safety-critical missions involving aerial vehicles.

## Summary

The successful landing of autonomous aerial vehicles on uncertain terrains, such as the Mars Science Laboratory Curiosity rover's landing on Mars, requires the ability to identify and reason about potentially hazardous landing sites. To address these challenges, a coupled perception-planning solution called HALO (Hazard-Aware Landing Optimization) is presented. The HALO framework combines two novel algorithms: Hazard-Aware Landing Site Selection (HALSS) and Adaptive Deferred-Decision Trajectory Optimization (Adaptive-DDTO). HALSS processes point cloud information to identify feasible safe landing zones while Adaptive-DDTO is a multi-target contingency planner that adaptively replans as new perception information is received. Using a simulated Martian environment, the authors demonstrate that their approach achieves greater landing success while being more fuel-efficient compared to a non-adaptive DDTO approach. The efficacy of HALO in addressing the challenges of autonomous landings makes it a promising solution for future safety-critical missions involving aerial vehicles.