A Maneuver-based Urban Driving Dataset and Model for Cooperative Vehicle Applications

Toghi, Behrad; Grover, Divas; Razzaghpour, Mahdi; Jain, Rajat; Valiente, Rodolfo; Zaman, Mahdi; Shah, G. N.; Fallah, Yaser P.

doi:10.1109/cavs51000.2020.9334665

Cited by 25 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different methods to predict or classify driver behaviors are based on driver attributes [46], graph theory [47], game theory [1] and data mining [48]. Toghi et al release a maneuver-based dataset and propose a model that can be used to classify driving maneuvers [28]. Authors in [44] present an approach to modeling and predicting human behavior in situations with several humans interacting in highly multimodal scenarios that could allow AVs to predict human reactions.…”

Section: A Driver Behavior and Social Navigationmentioning

confidence: 99%

Robustness and Adaptability of Reinforcement Learning based Cooperative Autonomous Driving in Mixed-autonomy Traffic

Valiente¹,

Toghi²,

Pedarsani³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Building autonomous vehicles (AVs) is a complex problem, but enabling them to operate in the real world where they will be surrounded by human-driven vehicles (HVs) is extremely challenging. Prior works have shown the possibilities of creating inter-agent cooperation between a group of AVs that follow a social utility. Such altruistic AVs can form alliances and affect the behavior of HVs to achieve socially desirable outcomes. We identify two major challenges in the co-existence of AVs and HVs. First, social preferences and individual traits of a given human driver, e.g., selflessness and aggressiveness are unknown to an AV, and it is almost impossible to infer them in real-time during a short AV-HV interaction. Second, contrary to AVs that are expected to follow a policy, HVs do not necessarily follow a stationary policy and therefore are extremely hard to predict. To alleviate the above-mentioned challenges, we formulate the mixed-autonomy problem as a multi-agent reinforcement learning (MARL) problem and propose a decentralized framework and reward function for training cooperative AVs. Our approach enables AVs to learn the decision-making of HVs implicitly from experience, optimizes for a social utility while prioritizing safety and allowing adaptability; robustifying altruistic AVs to different human behaviors and constraining them to a safe action space. Finally, we investigate the robustness, safety and sensitivity of AVs to various HVs behavioral traits and present the settings in which the AVs can learn cooperative policies that are adaptable to different situations.

show abstract

Section: A Driver Behavior and Social Navigationmentioning

confidence: 99%

Robustness and Adaptability of Reinforcement Learning based Cooperative Autonomous Driving in Mixed-autonomy Traffic

Valiente¹,

Toghi²,

Pedarsani³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…where µ i and σ i can be obtained from (5). Defining the cross validation objective function as the sum of the log-likelihoods over all most recent observations, i.e., L(t, V, α) = 5 i=1 log p (v i | t, V −i , α), the optimal parameters α * n = {γ * n , γ * n,noise } can be obtained using the conjugate gradient optimization method as proposed in [16].…”

Section: Stochastic Model-based Communicationmentioning

confidence: 99%

“…Upon receiving a packet, the receiving vehicle will use the newly received information for local control. Otherwise, in the case of packet loss, the cooperative vehicle will use the GP model to predict the velocity of the transmitting vehicle until receiving a new packet from it using (5).…”

Section: Stochastic Model-based Communicationmentioning

confidence: 99%

“…Connected and Autonomous Vehicles (CAVs) are required to frequently broadcast their dynamic and kinematic information over the wireless channel. The concept of information sharing among vehicles results in a level of situational awareness for any vehicle and makes it aware of its surrounding environment, crucial for the cooperative safety applications to function properly [5]. Although the cooperative vehicles' perception can be expanded to multiple predecessors' information by using vehicle to vehicle (V2V) communication, these technologies still suffer from scalability issues, especially in congested scenarios.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Impact of Information Flow Topology on Safety of Tightly-coupled Connected and Automated Vehicle Platoons Utilizing Stochastic Control

Razzaghpour¹,

Mosharafian²,

Raftari³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

“…Driving styles of humans can be learned from demonstration through inverse RL or employing statistical models [6], [14]- [16]. Modeling human driver behavior assists autonomous vehicles to identify potentials for creating cooperation and interaction opportunities with humans in order to realize safe and efficient navigation [17]. Moreover, human drivers are able to intuitively anticipate next actions of neighboring vehicles through observing slight changes in their trajectories and leverage the prediction to move proactively if required.…”

Section: Introductionmentioning

confidence: 99%

Cooperative Autonomous Vehicles that Sympathize with Human Drivers

Toghi¹,

Valiente²,

Sadigh³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Widespread adoption of autonomous vehicles will not become a reality until solutions are developed that enable these intelligent agents to co-exist with humans. This includes safely and efficiently interacting with human-driven vehicles, especially in both conflictive and competitive scenarios. We build up on the prior work on socially-aware navigation and borrow the concept of social value orientation from psychology -that formalizes how much importance a person allocates to the welfare of others-in order to induce altruistic behavior in autonomous driving. In contrast with existing works that explicitly model the behavior of human drivers and rely on their expected response to create opportunities for cooperation, our Sympathetic Cooperative Driving (SymCoDrive) paradigm trains altruistic agents that realize safe and smooth traffic flow in competitive driving scenarios only from experiential learning and without any explicit coordination. We demonstrate a significant improvement in both safety and traffic-level metrics as a result of this altruistic behavior and importantly conclude that the level of altruism in agents requires proper tuning as agents that are too altruistic also lead to sub-optimal traffic flow. The code and supplementary material are available at: https://symcodrive.toghi.net/

show abstract

A Maneuver-based Urban Driving Dataset and Model for Cooperative Vehicle Applications

Cited by 25 publications

References 13 publications

Robustness and Adaptability of Reinforcement Learning based Cooperative Autonomous Driving in Mixed-autonomy Traffic

Robustness and Adaptability of Reinforcement Learning based Cooperative Autonomous Driving in Mixed-autonomy Traffic

Impact of Information Flow Topology on Safety of Tightly-coupled Connected and Automated Vehicle Platoons Utilizing Stochastic Control

Cooperative Autonomous Vehicles that Sympathize with Human Drivers

Contact Info

Product

Resources

About