TRiLOGy: Sustainable Transportation and Logistics Over Water: Electrification, Automation, and Optimization

About the Project

TRiLOGy aims to unlock the potential of transportation and logistics in urban waterways with electric and autonomous vessels by enabling safer, more sustainable and efficient operations. The project aims at developing autonomy tools for navigation in inland waterways, among other manned and unmanned vessels. The main challenges to ensure safe and efficient navigation of autonomous vessels in urban waters is that of generating safe trajectories that (i) take into account the goals expressed by the high-level integrated strategy, (ii) take into account the complex dynamics of the vessel and (iii) coordinate with other traffic participants.

The main outcomes of the project were in the development of a motion planning algorithm, based on Model Predictive Path Integral (MPPI) control, that is able to generate safe trajectories for autonomous vessels in urban canals. The algorithm is able to take into account the dynamics of the vessel, the interactions with other traffic participants, as well as navigation rules, while also being able to adapt to changing environments and unexpected obstacles. The algorithm is designed to be used in real-time, allowing for fast and efficient navigation in complex environments.

Other developments include a robust controller for autonomous vessels, which is able to track reference trajectories in the presence of disturbances such as wind, waves and currents, which was tested in both harbour and open sea environments. We also worked on data collection, learning-based predictions, and transfer of the developed algorithms to ground robots and manipulators.

Project Demonstrations

We demonstrated our decentralized, rule- and interaction-aware MPPI planner running on-board two vessels. [1]

Crossing with Right-of-way

Head-on Encounter

With experiments on ground robots, we have shown the reactivity of the planner to unexpected dynamic obstacles [2] as well as the ability to plan accounting for prediction uncertainty [3].

Reactivity to Unexpected Obstacles

Risk-Aware Planning

In collaboration with project partners, we have collected real-world data onboards ships. We have also genereated large artificial datasets that we used to train a prediction model for vessels in urban canals [4].

Data Collection in Inland Waters

Planner with Learning-Based Predictions

In collaboration with Demcon, we have demonstrated a robust controller for reference tracking in harbour and open sea, showing good performance in the presence of wind, waves and currents [5].

Robust Control in Hourbour

Robust Control at Sea

Collaborating across projects, we have shown that the same planner used on vessels can be successfully used on ground robots and manipulators in contact rich tasks [6], [7].

Omnidirectional Push w Disturbances

Manipulator Push w Disturbances

Funding & Partners

This project is funded by the NWO Top Sector Water & Maritime: the Blue route, 'Sustainable Transportation and Logistics over Water: Electrification, Automation and Optimization (TRiLOGy)'.

Deploying mobile robots safely among humans requires the motion planner to account for the uncertainty in the other agents' predicted trajectories. This remains challenging in traditional approaches, especially with arbitrarily shaped predictions and real-time constraints. To address these challenges, we propose a Dynamic Risk-Aware Model Predictive Path Integral control (DRA-MPPI), a motion planner that incorporates uncertain future motions modelled with potentially non-Gaussian stochastic predictions. By leveraging MPPI's gradient-free nature, we propose a method that efficiently approximates the joint Collision Probability (CP) among multiple dynamic obstacles for several hundred sampled trajectories in real-time via a Monte Carlo (MC) approach. This enables the rejection of samples exceeding a predefined CP threshold or the integration of CP as a weighted objective within the navigation cost function. Consequently, DRA-MPPI mitigates the freezing robot problem while enhancing safety. Real-world and simulated experiments with multiple dynamic obstacles demonstrate DRA-MPPI's superior performance compared to state-of-the-art approaches, including Scenario-based Model Predictive Control (S-MPC), Frenét planner, and vanilla MPPI.

Unmanned Surface Vessels (USVs) face significant control challenges due to uncertain environmental disturbances like waves and currents. This paper proposes a trajectory tracking controller based on Active Disturbance Rejection Control (ADRC) implemented on the DUS V2500. A custom simulation incorporating realistic waves and current disturbances is developed to validate the controller's performance, supported by further validation through field tests in the harbour of Scheveningen, the Netherlands, and at sea. Simulation results demonstrate that ADRC significantly reduces cross-track error across all tested conditions compared to a baseline PID controller but increases control effort and energy consumption. Field trials confirm these findings while revealing a further increase in energy consumption during sea trials compared to the baseline.

We present a method for sampling-based model predictive control that makes use of a generic physics simulator as the dynamical model. In particular, we propose a Model Predictive Path Integral controller (MPPI), that uses the GPU-parallelizable IsaacGym simulator to compute the forward dynamics of a problem. By doing so, we eliminate the need for manual encoding of robot dynamics and interactions among objects and allow one to effortlessly solve complex navigation and contact-rich tasks. Since no explicit dynamic modeling is required, the method is easily extendable to different objects and robots. We demonstrate the effectiveness of this method in several simulated and real-world settings, among which mobile navigation with collision avoidance, non-prehensile manipulation, and whole-body control for high-dimensional configuration spaces. This method is a powerful and accessible tool to solve a large variety of contact-rich motion planning tasks.