Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Model Predictive Path Integral Docking of Fully Actuated Surface Vessel

Akash Vijayakumar, Atmanand M A, Abhilash Somayajula

TL;DR

This work addresses autonomous docking of unmanned surface vessels in confined spaces by integrating Model Predictive Path Integral (MPPI) control with real-time LiDAR-based dock detection and a multi-objective docking cost. The approach operates without reliance on prior maps, using probabilistic trajectory optimization to balance docking precision, safety, and efficiency, validated in a physics-based simulator with realistic sensor noise. The key contributions include a LiDAR-based dock processing pipeline (point cloud generation, clustering, wall estimation, clearance, and entry-point estimation) and a comprehensive, docking-specific cost formulation evaluated across varied initial poses. Findings indicate robust docking performance in frontal and lateral approaches, while highlighting limitations under limited visibility and suggesting future directions such as adaptive costs and learning-based reward design to improve generalization and real-world applicability.

Abstract

Autonomous docking remains one of the most challenging maneuvers in marine robotics, requiring precise control and robust perception in confined spaces. This paper presents a novel approach integrating Model Predictive Path Integral(MPPI) control with real-time LiDAR-based dock detection for autonomous surface vessel docking. Our framework uniquely combines probabilistic trajectory optimization with a multiobjective cost function that simultaneously considers docking precision, safety constraints, and motion efficiency. The MPPI controller generates optimal trajectories by intelligently sampling control sequences and evaluating their costs based on dynamic clearance requirements, orientation alignment, and target position objectives. We introduce an adaptive dock detection pipeline that processes LiDAR point clouds to extract critical geometric features, enabling real-time updates of docking parameters. The proposed method is extensively validated in a physics-based simulation environment that incorporates realistic sensor noise, vessel dynamics, and environmental constraints. Results demonstrate successful docking from various initial positions while maintaining safe clearances and smooth motion characteristics.

Model Predictive Path Integral Docking of Fully Actuated Surface Vessel

TL;DR

This work addresses autonomous docking of unmanned surface vessels in confined spaces by integrating Model Predictive Path Integral (MPPI) control with real-time LiDAR-based dock detection and a multi-objective docking cost. The approach operates without reliance on prior maps, using probabilistic trajectory optimization to balance docking precision, safety, and efficiency, validated in a physics-based simulator with realistic sensor noise. The key contributions include a LiDAR-based dock processing pipeline (point cloud generation, clustering, wall estimation, clearance, and entry-point estimation) and a comprehensive, docking-specific cost formulation evaluated across varied initial poses. Findings indicate robust docking performance in frontal and lateral approaches, while highlighting limitations under limited visibility and suggesting future directions such as adaptive costs and learning-based reward design to improve generalization and real-world applicability.

Abstract

Autonomous docking remains one of the most challenging maneuvers in marine robotics, requiring precise control and robust perception in confined spaces. This paper presents a novel approach integrating Model Predictive Path Integral(MPPI) control with real-time LiDAR-based dock detection for autonomous surface vessel docking. Our framework uniquely combines probabilistic trajectory optimization with a multiobjective cost function that simultaneously considers docking precision, safety constraints, and motion efficiency. The MPPI controller generates optimal trajectories by intelligently sampling control sequences and evaluating their costs based on dynamic clearance requirements, orientation alignment, and target position objectives. We introduce an adaptive dock detection pipeline that processes LiDAR point clouds to extract critical geometric features, enabling real-time updates of docking parameters. The proposed method is extensively validated in a physics-based simulation environment that incorporates realistic sensor noise, vessel dynamics, and environmental constraints. Results demonstrate successful docking from various initial positions while maintaining safe clearances and smooth motion characteristics.
Paper Structure (27 sections, 25 equations, 6 figures, 1 table)

This paper contains 27 sections, 25 equations, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. References and Related Work
  3. Model Predictive Path Integral (MPPI) Algorithm
  4. Algorithm Overview
  5. Advantages of MPPI
  6. Simulation Environment
  7. Vessel Dynamics
  8. Physical Environment
  9. Sensor Simulation
  10. Collision Detection
  11. Lidar Scan Processing
  12. Point Cloud Generation
  13. Clustering and Dock Identification
  14. Wall Segmentation and Orientation Estimation
  15. Clearance Calculation
  16. ...and 12 more sections

Figures (6)

  • Figure 1: Simulation Environment
  • Figure 2: Dock Point Cloud Segmentation
  • Figure 3: Scenario 1
  • Figure 4: Scenario 2
  • Figure 5: Scenario 3
  • ...and 1 more figures