Pedestrians follow different trajectories to avoid obstacles and accommodate fellow pedestrians. Any autonomous vehicle navigating such a scene should be able to foresee the future positions of pedestrians and accordingly adjust its path to avoid collisions. This problem of trajectory prediction can be viewed as a sequence generation task, where we are interested in predicting the future trajectory of people based on their past positions. Following the recent success of Recurrent Neural Network (RNN) models for sequence prediction tasks, we propose an LSTM model which can learn general human movement and predict their future trajectories. This is in contrast to traditional approaches which use hand-crafted functions such as Social forces. We demonstrate the performance of our method on several public datasets. Our model outperforms state-of-the-art methods on some of these datasets. We also analyze the trajectories predicted by our model to demonstrate the motion behaviour learned by our model.

/pdf/social-lstm-human-trajectory-prediction-in-crowded-spaces-wwxok9svq7.pdf

Social LSTM: Human Trajectory Prediction in Crowded Spaces

Most of the signal processing that we will study in this course involves local operations on a signal, namely transforming the signal by applying linear combinations of values in the neighborhood of each sample point. You are familiar with such operations from Calculus, namely, taking derivatives and you are also familiar with this from optics namely blurring a signal. We will be looking at sampled signals only. Let's start with a few basic examples. Local difference Suppose we have a 1D image and we take the local difference of intensities, DI(x) = 1 2 (I(x + 1) − I(x − 1)) which give a discrete approximation to a partial derivative. (We compute this for each x in the image.) What is the effect of such a transformation? One key idea is that such a derivative would be useful for marking positions where the intensity changes. Such a change is called an edge. It is important to detect edges in images because they often mark locations at which object properties change. These can include changes in illumination along a surface due to a shadow boundary, or a material (pigment) change, or a change in depth as when one object ends and another begins. The computational problem of finding intensity edges in images is called edge detection. We could look for positions at which DI(x) has a large negative or positive value. Large positive values indicate an edge that goes from low to high intensity, and large negative values indicate an edge that goes from high to low intensity. Example Suppose the image consists of a single (slightly sloped) edge:

http://ieeexplore.ieee.org/iel5/5/31307/01456462.pdf

Linear systems

Intelligent vehicle cooperation based on reliable communication systems contributes not only to reducing traffic accidents but also to improving traffic flow. Adaptive cruise control (ACC) systems can gain enhanced performance by adding vehicle-vehicle wireless communication to provide additional information to augment range sensor data, leading to cooperative ACC (CACC). This paper presents the design, development, implementation, and testing of a CACC system. It consists of two controllers, one to manage the approaching maneuver to the leading vehicle and the other to regulate car-following once the vehicle joins the platoon. The system has been implemented on four production Infiniti M56s vehicles, and this paper details the results of experiments to validate the performance of the controller and its improvements with respect to the commercially available ACC system.

/pdf/cooperative-adaptive-cruise-control-in-real-traffic-35mggeon75.pdf

Cooperative Adaptive Cruise Control in Real Traffic Situations

Unmanned surface vehicles: An overview of developments and challenges

With growing numbers of intelligent autonomous systems in human environments, the ability of such systems to perceive, understand, and anticipate human behavior becomes increasingly important. Spec...

Human motion trajectory prediction: a survey:

RoboEarth - A World Wide Web for Robots

The design of a CACC system and corresponding experiments are presented. The design targets string stable system behavior, which is assessed using a frequency-domain-based approach. Following this approach, it is shown that the available wireless information enables small inter-vehicle distances, while maintaining string stable behavior. The theoretical results are validated by experiments with two CACC-equipped vehicles. Measurement results showing string stable as well as string unstable behavior are discussed.

/pdf/cooperative-adaptive-cruise-control-design-and-experiments-tyv5vxv9br.pdf

Cooperative adaptive cruise control, design and experiments

Deceleration rates have considerable influence on the fuel economy of hybrid electric vehicles. Given the vehicle characteristics and actual/measured operating conditions, as well as upcoming route information, optimal velocity trajectories can be constructed that maximize energy recovery. To support the driver in tracking of the energy optimal velocity trajectory, automatic cruise control is an important driver aid. In practice, perfect tracking of the optimal velocity trajectory is often not possible. An Adaptive Cruise Control (ACC) system is employed to react to the actual traffic situation. The combination of optimal velocity trajectory construction and ACC is presented as Predictive Cruise Control (PCC).

/pdf/predictive-cruise-control-in-hybrid-electric-vehicles-1xj71cjikp.pdf

Predictive Cruise Control in Hybrid Electric Vehicles

In this paper, we present the core concept and the benefits of an approach called RoboEarth which will be highly beneficial for future robotic applications in science and industry. RoboEarth is a world-wide platform which robots can use to exchange position and map information as well as task-related, hardware-independent action recipes. This will enable manufacturers worldwide to break down their costs and efforts for reproducing software algorithms for robot behavior over and over again. The RoboEarth framework can store all relevant data from algorithms to complex behavior descriptions what allows robots to act autonomously in an unknown, unspecified environment. Especially in the field of interaction with humans RoboEarth can bring forward the behavior of robots and simplify the software design for developers in that field.

http://www.dct.tue.nl/RoboEarth/RoboEarth.pdf

RoboEarth: connecting robots worldwide

Atomic Force Microscopes (AFMs) are widely used for the investigation of samples at the nanometer scale. The metrological AFM used in this work uses a 3 degrees-of-freedom (DOFs) stage, driven by piezo-stack actuators, for sample manipulation in combination with a fixed cantilever. The piezostack actuators suffer from hysteresis, which acts as a nonlinear disturbance on the system and/or can change the system dynamics. The contributions of this paper are the application of feedback control to all 3 DOFs of the metrological AFM and the design and application of a hysteresis feedforward for the asymmetric hysteresis present in the system. The amount of coupling between the DOFs is assessed by a non-parametric multiple-input-multipleoutput (MIMO) identification. Since the dynamics appear to be decoupled in the frequency range of interest, feedback controllers are designed for each DOF separately. For the modeling of the asymmetric hysteresis an extended Coleman-Hodgdon model is proposed. This model is used for feedforward compensation of the hysteresis. The combination of feedback control for all DOFs and the asymmetric hysteresis feedforward enables the AFM to track scanning profiles within the sensor bound of 5nm. Real-time imaging of the sample is possible with an accuracy of 2nm.

http://www.mate.tue.nl/mate/pdfs/9726.pdf

René van de Molengraft

Papers

RoboEarth - A World Wide Web for Robots

Cooperative adaptive cruise control, design and experiments

Predictive Cruise Control in Hybrid Electric Vehicles

RoboEarth: connecting robots worldwide

Identification, control and hysteresis compensation of a 3 dof metrological afm