Online Parameter Estimation for Human Driver Behavior Prediction

Bhattacharyya, Raunak P.; Senanayake, Ransalu; Brown, Kyle; Kochenderfer, Mykel J.

doi:10.23919/acc45564.2020.9147924

Cited by 27 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This presents the great potential of combining model-based approaches and learning frameworks, which can produce both safer and more realistic models for human road users. Results on NGSIM and HighD: We first test our approach for NGSIM and HighD datasets under low density traffic (20 agents, no non-reactive agents, 5 seconds) as what was used in [41]. We compare with IDM θ [41], PS-GAIL [19] (a) Comparison for driver-related metrics with the expert policy, PS-GAIL and RAIL using the same training/testing splits as in [19] and [8].…”

Section: B Main Resultsmentioning

confidence: 99%

“…We use the original implementation of RAIL provided by the authors. Lastly, we compare with a state-of-the-art (none-learning) calibration methods IDM θ [41] on NGSIM and HighD. Again the IDM θ models in [41] could only work for highway car-following cases so we do not compare with it on other datasets.…”

Section: A Implementation Details Baseline and Metricsmentioning

confidence: 99%

“…Lastly, we compare with a state-of-the-art (none-learning) calibration methods IDM θ [41] on NGSIM and HighD. Again the IDM θ models in [41] could only work for highway car-following cases so we do not compare with it on other datasets. Metrics: We compute the following measurements for safety and similarity to real-world data: Collision rate reflects systems' safety, and is calculated by the number of agent states that fall into the unsafe set divided by the total number of agent states.…”

Section: A Implementation Details Baseline and Metricsmentioning

confidence: 99%

See 2 more Smart Citations

Reactive and Safe Road User Simulations using Neural Barrier Certificates

Meng¹,

Qin²,

Fan³

2021

Preprint

View full text Add to dashboard Cite

Reactive and safe agent modellings are important for nowadays traffic simulator designs and safe planning applications. In this work, we proposed a reactive agent model which can ensure safety without comprising the original purposes, by learning only high-level decisions from expert data and a low level decentralized controller guided by the jointly learned decentralized barrier certificates. Empirical results show that our learned road user simulation models can achieve a significant improvement in safety comparing to state-of-theart imitation learning and pure control-based methods, while being similar to human agents by having smaller error to the expert data. Moreover, our learned reactive agents are shown to generalize better to unseen traffic conditions, and react better to other road users and therefore can help understand challenging planning problems pragmatically.

show abstract

Section: B Main Resultsmentioning

confidence: 99%

Section: A Implementation Details Baseline and Metricsmentioning

confidence: 99%

Section: A Implementation Details Baseline and Metricsmentioning

confidence: 99%

See 1 more Smart Citation

Reactive and Safe Road User Simulations using Neural Barrier Certificates

Meng¹,

Qin²,

Fan³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We compare our algorithm with a baseline method, continuous inverse optimal control (CIOC) [3], [49], which is an IOC algorithm for large, continuous domains and does not assume any feedback interaction among the observed agents. Additionally, for the INTERACTION dataset, we also compare with the intelligent driver model (IDM) [6], [50] as our reference model. IDM is a widely used expert-designed model to simulate traffic flow that is known to yield accurate predictions of drivers' trajectories.…”

Section: Methodsmentioning

confidence: 99%

Maximum-Entropy Multi-Agent Dynamic Games: Forward and Inverse Solutions

Mehr¹,

Wang²,

Schwager³

2021

Preprint

View full text Add to dashboard Cite

In this paper, we study the problem of multiple stochastic agents interacting in a dynamic game scenario with continuous state and action spaces. We define a new notion of stochastic Nash equilibrium for boundedly rational agents, which we call the Entropic Cost Equilibrium (ECE). We show that ECE is a natural extension to multiple agents of Maximum Entropy optimality for single agents. We solve both the "forward" and "inverse" problems for the multi-agent ECE game. For the forward problem, we provide a Riccati algorithm to compute closed-form ECE feedback policies for the agents, which are exact in the Linear-Quadratic-Gaussian case. We give an iterative variant to find locally ECE feedback policies for the nonlinear case. For the inverse problem, we present an algorithm to infer the cost functions of the multiple interacting agents given noisy, boundedly rational input and state trajectory examples from agents acting in an ECE. The effectiveness of our algorithms is demonstrated in a simulated multi-agent collision avoidance scenario, and with data from the INTERACTION traffic dataset. In both cases, we show that, by taking into account the agents' game theoretic interactions using our algorithm, a more accurate model of agents' costs can be learned, compared with standard inverse optimal control methods.

show abstract

“…To generate safe and kamikaze trajectories, the testing mechanism needs to have a predictive model of the car's behaviour, albeit imperfect. For this purpose, many work can be adopted, such as [4,10,14,20]. Our kamikaze trajectory generation can also benefit from work on pursuit evasion [7] and more recently [16], though the latter is focused on deforming observations rather than an adversary's behaviour.…”

Section: Related Workmentioning

confidence: 99%

An NCAP-like Safety Indicator for Self-Driving Cars

Huang,

Kurniawati

2021

Preprint

View full text Add to dashboard Cite

This paper proposes a mechanism to assess the safety of autonomous cars. It assesses the car's safety in scenarios where the car must avoid collision with an adversary. Core to this mechanism is a safety measure, called Safe-Kamikaze Distance (SKD), which computes the average similarity between sets of safe adversary's trajectories and kamikaze trajectories close to the safe trajectories. The kamikaze trajectories are generated based on planning under uncertainty techniques, namely the Partially Observable Markov Decision Processes, to account for the partially observed car policy from the point of view of the adversary. We found that SKD is inversely proportional to the upper bound on the probability that a small deformation changes a collision-free trajectory of the adversary into a colliding one. We perform systematic tests on a scenario where the adversary is a pedestrian crossing a single-lane road in front of the car being assessed -which is, one of the scenarios in the Euro-NCAP's Vulnerable Road User (VRU) tests on Autonomous Emergency Braking. Simulation results on assessing cars with basic controllers and a test on a Machine-Learning controller using a high-fidelity simulator indicates promising results for SKD to measure the safety of autonomous cars. Moreover, the time taken for each simulation test is under 11 seconds, enabling a sufficient statistics to compute SKD from simulation to be generated on a quad-core desktop in less than 25 minutes.

show abstract

Online Parameter Estimation for Human Driver Behavior Prediction

Cited by 27 publications

References 24 publications

Reactive and Safe Road User Simulations using Neural Barrier Certificates

Reactive and Safe Road User Simulations using Neural Barrier Certificates

Maximum-Entropy Multi-Agent Dynamic Games: Forward and Inverse Solutions

An NCAP-like Safety Indicator for Self-Driving Cars

Contact Info

Product

Resources

About