SAFEVRU

People

Oscar de Groot - PhD Candidate

Prof. Laura Ferranti

Prof. Javier Alonso-Mora

Prof. Dariu Gavrila

Funding

This work is funded by the Dutch Science Foundation NWO-TTW Foundation, within the SafeVRU project

About the Project

Every year between 20 and 50 million people are involved in road accidents caused mainly by human erros. A large number of these victims are vulnerable road users (VRUs) such as pedestrians and cyclists. Self driving vehicles are expected to help reduce these fatalities. However, in order for this to be accomplised, appropriate functionalities and rigorous testing must be carried out to ensure its working. The self driving vehicle must be aware of the presence of VRUs and plan its path accordinglt ro prevent collisions. This project presents a research platform SafeVRU which is a self driving vehicle that is able to plan trajectories in the presence of VRUs. Several realistic scenarios have been tested such as a cyclist approach the vehicle in an intersection or pedestrians crossing the road in front of the vehicle.

The SafeVRU platform firstly has a perception module which provides the planner information about the position and predicted paths of the other road users. These predictions are then used in the planning module which is a model predictive contouring controller (MPCC). The MPCC plans a collision-free path for the vehicle over a time window. To provide additional safety, this planner prevents the vehicle from approaching really close to a road user. Real-life experiments showed that the vehicle was able to adapt to different initial conditions and in all the cases, the local planner provided suitable paths which ensured safety of the VRUs detected.

Another contribution of this project in addition to the platform is an optimisation method that can be used for motion planning in uncertain dynamic environments. This is especially useful when vehicles have to operate around humans. The proposed framework is termed as scenario-based model predictive contouring control (S-MPCC) and can handle multiple obstacles while accounting for their respective sizes. This allows the vehicle to move continuously while tracking its probability of colliding with nearby obstacles. This method was experimentally validated using a moving robot platform that had to navigate among pedestrians in real-time.

Project Demonstrations

Funding & Partners

This work is funded by the Dutch Science Foundation NWO-TTW Foundation, within the SafeVRU project

Globally Guided Trajectory Planning in Dynamic Environments
O. de Groot, L. Ferranti, D. Gavrila, J. Alonso-Mora. In IEEE Int. Conf. on Robotics and Automation (ICRA), 2023.

abstract pdf video

Navigating mobile robots through environments shared with humans is challenging. From the perspective of the robot, humans are dynamic obstacles that must be avoided. These obstacles make the collision-free space nonconvex, which leads to two distinct passing behaviors per obstacle (passing left or right). For local planners, such as receding-horizon trajectory optimization, each behavior presents a local optimum in which the planner can get stuck. This may result in slow or unsafe motion even when a better plan exists. In this work, we identify trajectories for multiple locally optimal driving behaviors, by considering their topology. This identification is made consistent over successive iterations by propagating the topology information. The most suitable high-level trajectory guides a local optimization-based planner, resulting in fast and safe motion plans. We validate the proposed planner on a mobile robot in simulation and real-world experiments.

Scenario-Based Trajectory Optimization in Uncertain Dynamic Environments
O. de Groot, B. Brito, L. Ferranti, D. Gavrila, J. Alonso-Mora. In , IEEE Robotics and Automation Letters (RA-L), 2021.

abstract arxiv pdf video

We present an optimization-based method to plan the motion of an autonomous robot under the uncertainties associated with dynamic obstacles, such as humans. Our method bounds the marginal risk of collisions at each point in time by incorporating chance constraints into the planning problem. This problem is not suitable for online optimization outright for arbitrary probability distributions. Hence, we sample from these chance constraints using an uncertainty model, to generate "scenarios", which translate the probabilistic constraints into deterministic ones. In practice, each scenario represents the collision constraint for a dynamic obstacle at the location of the sample. The number of theoretically required scenarios can be very large. Nevertheless, by exploiting the geometry of the workspace, we show how to prune most scenarios before optimization and we demonstrate how the reduced scenarios can still provide probabilistic guarantees on the safety of the motion plan. Since our approach is scenario based, we are able to handle arbitrary uncertainty distributions. We apply our method in a Model Predictive Contouring Control framework and demonstrate its benefits in simulations and experiments with a moving robot platform navigating among pedestrians, running in real-time.

SafeVRU: A Research Platform for the Interaction of Self-Driving Vehicles with Vulnerable Road Users
L. Ferranti, B. Brito, E. Pool, Y. Zheng, R. M. Ensing, R. Happee, B. Shyrokau, J. Kooij, J. Alonso-Mora, D. M. Gavrila. In Proc. IEEE Intelligent Vehicles Symposium, 2019.

abstract publisher pdf video

This paper presents our research platform Safe VRU for the interaction of self-driving vehicles with Vulnerable Road Users (VRUs, i.e., pedestrians and cyclists). The paper details the design (implemented with a modular structure within ROS) of the full stack of vehicle localization, environment perception, motion planning, and control, with emphasis on the environment perception and planning modules. The environment perception detects the VRUs using a stereo camera and predicts their paths with Dynamic Bayesian Networks (DBNs), which can account for switching dynamics. The motion planner is based on model predictive contouring control (MPCC) and takes into account vehicle dynamics, control objectives (e.g., desired speed), and perceived environment (i.e., the predicted VRU paths with behavioral uncertainties) over a certain time horizon. We present simulation and real-world results to illustrate the ability of our vehicle to plan and execute collision-free trajectories in the presence of VRUs.