Analyze approaches in long-term agents motion prediction

2.2.1 Long-term Vehicle Motion Prediction (Hermes et al., 2009)

A long-term prediction approach based on a combined definition of the trajectories and a particle filter structure is suggested by this method. As a measure for similarities between trajectories, let the quaternion-based rotationally invariant longest common subsequence (QRLCS) metric be used. (Hermes et al., 2009) The trajectories are categorized by a radial base function (RBF) classifier with an architecture that is capable of handling arbitrary non-uniform length trajectories. (Hermes et al., 2009) The particle filter system monitors and tests a large number of motion hypotheses at the same time (nearly 102), where the class-specific probabilities determined by the RBF classifier are used for particle filter hypotheses as a-priority probabilities. (Hermes et al., 2009) The hypotheses are clustered using a mean-shift procedure, and assigned a probability value. Based on the cluster core, motion prediction is achieved with the greatest likelihood. (Hermes et al., 2009)

41

This paper was used the mostly for the algorithms insight and a current state of the art in the field of autonomous driving. Its approach for prediction and assessment of the road situation is used as an example of a state of art algorithm for comparison with the developing system in this work.

In addition, the evaluation methodology from this work plays a significant role for this work. It is used as one of the basements for evaluation methodology of this work, which will be described more in the section about evaluation.

2.2.2 A survey on motion prediction and risk assessment for intelligent vehicles (Lefèvre, Vasquez and Laugier, 2014)

This approach is a review of current approaches for intelligent vehicles for motion prediction and risk assessment. The proposed classification is based on the semantics used to describe movement and risk. (Lefèvre, Vasquez and Laugier, 2014)

The tradeoff between the completeness of the model and real-time constraints and the fact that the selected motion model determines the choice of a method for risk assessment is pointed out. (Lefèvre, Vasquez and Laugier, 2014)

In order to assess the risk associated with a specific situation, this paper surveys mathematical models that allow us to predict how the situation will develop in the future and their relationship to risk assessment. (Lefèvre, Vasquez and Laugier, 2014) According to the kind of assumptions they create about the modelled entities, we may choose to arrange motion modeling and pre-diction approaches. (Lefèvre, Vasquez and Laugier, 2014)

The study proposes a classification with a growing degree of abstraction at two levels:

 Physics-based motion models are the simplest models, given that vehicle movement depends only on the physical laws. (Lefèvre, Vasquez and Laugier, 2014)

42

 Maneuver-based motion models are more advanced because they assume that a vehicle's potential movement often relies on the maneuver the driver wants to produce. (Lefèvre, Vasquez and Laugier, 2014) Interaction-aware motion models take into account the interdependencies between the vehicles' maneuvers. . (Lefèvre, Vasquez and Laugier, 2014)

This paper very helps when it comes to the motion modeling and trajectory prediction. Its useful insight on risk assessment of vehicles motion helps to understand what is the current level of risk assessment and what should the developer of motion prediction model consider first when it comes to this criteria.

Some of the insights from this paper can be seen in the part which describes relevance of undertaking research.

2.2.3 How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Prediction (Deo, Rangesh and Trivedi, 2018)

An ablative analysis that is carried out to evaluate the relative value of each cue for trajectory prediction is defined in this approach. (Deo, Rangesh and Trivedi, 2018) In addition, an overview is provided of the execution time for framework components.

(Deo, Rangesh and Trivedi, 2018)

It presents numerous case studies that examine the outputs of our model for complex traffic scenarios. (Deo, Rangesh and Trivedi, 2018) Index words — Detection of maneuvers, interaction-aware prediction of motion, mounted vehicle cameras, variational Gaussian mixture (VGMM), Hidden Markov Models (HMM). (Deo, Rangesh and Trivedi, 2018)

This paper helps with its useful insight on the one of the best approaches in the field of autonomous driving and agent trajectory prediction.

It is used as a knowledge source in the evaluation part of this work where some of the techniques were used, which will be described more in an appropriate section about developing model evaluation.

43

2.2.4 Probabilistic Prediction from Planning Perspective: Problem Formulation, Representation Simplification and Evaluation Metric (Zhan et al., 2018)

This approach offers a systematic and coherent context for three less studied aspects of probabilistic prediction to be analyzed: problem formulation, representation simplification, and evaluation metric. (Zhan et al., 2018) Measures to be interpreted from a planning perspective are demonstrated in addition to an analysis of learning measures, such as planning effects of incorrect and inaccurate prediction, as well as breaches of anticipated motions to planning constraints. (Zhan et al., 2018)

In this research, participants address practical variations in the formulation of prediction problems, such as the view of decision-makers and the blind view of perspective, as well as reactive interaction prediction, so that it is possible to promote decision-making and planning. (Zhan et al., 2018)

This paper provides a useful insight on the planning prediction algorithms with a detailed mathematical explanation which really helps in designing and developing prediction models. In particular, some of its insights will be seen in a section of this work which describes problematics of the surrounding agents motion prediction.

2.2.5 Multi-Modal Trajectory Prediction of Surrounding Vehicles with Maneuver based LSTMs (Deo and Trivedi, 2018)

An LSTM model for interaction-conscious motion prediction of nearby vehicles on freeways is provided in this approach. (Deo and Trivedi, 2018)

Defined model assigns trust values to vehicle maneuvers and outputs a multi-modal distribution based on them over future motion. (Deo and Trivedi)

This paper gives a significant insight on the usage of such advanced algorithms as LSTMs which is a more advanced for of the recurrent neural networks used for sequences prediction while assessing and planning trajectories.

44

2.2.6 Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks (Cui et al., 2019)

This approach tackles the crucial problem of traffic behavior complexity and a large number of situations an SDV may encounter on the roads, making it very difficult to construct a completely generalizable framework and provides a tool for predicting several potential actor trajectories while also estimating their likelihoods. (Cui et al., 2019)

The method encodes each actor's ambient context into a raster image, which is used as input by large, convolutional networks to automatically extract suitable mission functions. (Cui et al., 2019) After comprehensive offline evaluation and comparison with state-of-the-art baselines the device was successfully validated on SDVs in closed-course experiments. (Cui et al., 2019)

2.3 Analyze existing approaches in long-term prediction of