Robust and Real-Time Detection and Tracking of Moving Objects with Minimum 2D LiDAR Information to Advance Autonomous Cargo Handling in Ports

Abstract

Detecting and tracking moving objects (DATMO) is an essential component for autonomous driving and transportation. In this paper, we present a computationally low-cost and robust DATMO system which uses as input only 2D laser rangefinder (LRF) information. Due to its low requirements both in sensor needs and computation, our DATMO algorithm is meant to be used in current Autonomous Guided Vehicles (AGVs) to improve their reliability for the cargo transportation tasks at port terminals, advancing towards the next generation of fully autonomous transportation vehicles. Our method follows a Detection plus Tracking paradigm. In the detection step we exploit the minimum information of 2D-LRFs by segmenting the elements of the scene in a model-free way and performing a fast object matching to pair segmented elements from two different scans. In this way, we easily recognize dynamic objects and thus reduce consistently by between two and five times the computational burden of the adjacent tracking method. We track the final dynamic objects with an improved Multiple-Hypothesis Tracking (MHT), to which special functions for filtering, confirming, holding, and deleting targets have been included. The full system is evaluated in simulated and real scenarios producing solid results. Specifically, a simulated port environment has been developed to gather realistic data of common autonomous transportation situations such as observing an intersection, joining vehicle platoons, and perceiving overtaking maneuvers. We use different sensor configurations to demonstrate the robustness and adaptability of our approach. We additionally evaluate our system with real data collected in a port terminal the Netherlands. We show that it is able to accomplish the vehicle following task successfully, obtaining a total system recall of more than 98% while running faster than 30 Hz.

Adaptive Side-by-Side Social Robot Navigation to Approach and Interact with People

“…Then, we selected exactly the person to accompany and the person to approach, because the autonomous recognition and differentiation from other people is out of the scope of the work. All people were detected using a laser leg detector and tracked using a multi-hypothesis tracker, published in [64]. We developed the same five sets of experiments of the companion case, but this time the final destination was dynamic, it corresponded to the movement of the target person that the group wanted to approach.…”

People’s V-Formation and Side-by-Side Model Adapted to Accompany Groups of People by Social Robots

“…The robot is socially accepted and humans take interest in interacting with it. All people in the environment were detected using a laser leg detector and tracked using a multi-hypothesis tracker [28] that differentiates each people using an identifier. Then, as differentiating the accompanied people is out of the scope of this paper, we selected these people by proximity at the beginning of the experiment and keep track of them during all the experiment.…”

Perception Sensors for Road Applications

“…A computationally low-cost and robust detecting and tracking moving objects (DATMO) system, which uses as input only 2D laser rangefinder information, is presented in Reference [5]. Due to its low requirements, both in sensor needs and computation, the DATMO algorithm is meant to be used in current autonomous guided vehicles to improve their reliability for the cargo transportation tasks at port terminals, advancing towards the next generation of fully autonomous transportation vehicles.…”