Search

This paper presents an online smooth-path lane-change control framework. We focus on dense traffic where inter-vehicle space gaps are narrow, and cooperation with surrounding drivers is essential to achieve the lane-change maneuver. We propose a two-stage control framework that harmonizes Model Predictive Control (MPC) with Generative Adversarial Networks (GAN) by utilizing driving intentions to generate smooth lane-change maneuvers. To improve performance in practice, the system is augmented with an adaptive safety boundary and a Kalman Filter to mitigate sensor noise. Simulation studies are investigated in different levels of traffic density and cooperativeness of other drivers. The simulation results support the effectiveness, driving comfort, and safety of the proposed method.

This paper introduces a novel numerical approach to achieving smooth lane-change trajectories in autonomous driving scenarios. Our trajectory generation approach leverages particle swarm optimization (PSO) techniques, incorporating Neural Network (NN) predictions for trajectory refinement. The generation of smooth and dynamically feasible trajectories for the lane change maneuver is facilitated by combining polynomial curve fitting with particle propagation, which can account for vehicle dynamics. The proposed planning algorithm is capable of determining feasible trajectories with real-time computation capability. We conduct comparative analyses with two baseline methods for lane changing, involving analytic solutions and heuristic techniques in numerical simulations. The simulation results validate the efficacy and effectiveness of our proposed approach.

Smooth and safe speed planning is imperative for the successful deployment of autonomous vehicles. This paper presents a mathematical formulation for the optimal speed planning of autonomous driving, which has been validated in high-fidelity simulations and real-road demonstrations with practical constraints. The algorithm explores the inter-traffic gaps in the time and space domain using a breadth-first search. For each gap, quadratic programming finds an optimal speed profile, synchronizing the time and space pair along with dynamic obstacles. Qualitative and quantitative analysis in Carla is reported to discuss the smoothness and robustness of the proposed algorithm. Finally, we present a road demonstration result for urban city driving., Comment: Submitted to ICRA 2024

Real-world driving involves intricate interactions among vehicles navigating through dense traffic scenarios. Recent research focuses on enhancing the interaction awareness of autonomous vehicles to leverage these interactions in decision-making. These interaction-aware planners rely on neural-network-based prediction models to capture inter-vehicle interactions, aiming to integrate these predictions with traditional control techniques such as Model Predictive Control. However, this integration of deep learning-based models with traditional control paradigms often results in computationally demanding optimization problems, relying on heuristic methods. This study introduces a principled and efficient method for combining deep learning with constrained optimization, employing knowledge distillation to train smaller and more efficient networks, thereby mitigating complexity. We demonstrate that these refined networks maintain the problem-solving efficacy of larger models while significantly accelerating optimization. Specifically, in the domain of interaction-aware trajectory planning for autonomous vehicles, we illustrate that training a smaller prediction network using knowledge distillation speeds up optimization without sacrificing accuracy.

This paper proposes a hierarchical autonomous vehicle navigation architecture, composed of a high-level speed and lane advisory system (SLAS) coupled with low-level trajectory generation and trajectory following modules. Specifically, we target a multi-lane highway driving scenario where an autonomous ego vehicle navigates in traffic. We propose a novel receding horizon mixed-integer optimization based method for SLAS with the objective to minimize travel time while accounting for passenger comfort. We further incorporate various modifications in the proposed approach to improve the overall computational efficiency and achieve real-time performance. We demonstrate the efficacy of the proposed approach in contrast to the existing methods, when applied in conjunction with state-of-the-art trajectory generation and trajectory following frameworks, in a CARLA simulation environment., Comment: Presented at the IEEE 61st Conference on Decision and Control (CDC), Cancun, Mexico, 2022

The ability to accurately predict others' behavior is central to the safety and efficiency of interactive robotics. Unfortunately, robots often lack access to key information on which these predictions may hinge, such as other agents' goals, attention, and willingness to cooperate. Dual control theory addresses this challenge by treating unknown parameters of a predictive model as stochastic hidden states and inferring their values at runtime using information gathered during system operation. While able to optimally and automatically trade off exploration and exploitation, dual control is computationally intractable for general interactive motion planning. In this paper, we present a novel algorithmic approach to enable active uncertainty reduction for interactive motion planning based on the implicit dual control paradigm. Our approach relies on sampling-based approximation of stochastic dynamic programming, leading to a model predictive control problem that can be readily solved by real-time gradient-based optimization methods. The resulting policy is shown to preserve the dual control effect for a broad class of predictive models with both continuous and categorical uncertainty. To ensure the safe operation of the interacting agents, we use a runtime safety filter (also referred to as a "shielding" scheme), which overrides the robot's dual control policy with a safety fallback strategy when a safety-critical event is imminent. We then augment the dual control framework with an improved variant of the recently proposed shielding-aware robust planning scheme, which proactively balances the nominal planning performance with the risk of high-cost emergency maneuvers triggered by low-probability agent behaviors. We demonstrate the efficacy of our approach with both simulated driving studies and hardware experiments using 1/10 scale autonomous vehicles., Comment: The International Journal of Robotics Research. arXiv admin note: text overlap with arXiv:2202.07720

Accurately modeling the behavior of traffic participants is essential for safely and efficiently navigating an autonomous vehicle through heavy traffic. We propose a method, based on the intelligent driver model, that allows us to accurately model individual driver behaviors from only a small number of frames using easily observable features. On average, this method makes prediction errors that have less than 1 meter difference from an oracle with full-information when analyzed over a 10-second horizon of highway driving. We then validate the efficiency of our method through extensive analysis against a competitive data-driven method such as Reinforcement Learning that may be of independent interest.

The ability to estimate human intentions and interact with human drivers intelligently is crucial for autonomous vehicles to successfully achieve their objectives. In this paper, we propose a game theoretic planning algorithm that models human opponents with an iterative reasoning framework and estimates human latent cognitive states through probabilistic inference and active learning. By modeling the interaction as a partially observable Markov decision process with adaptive state and action spaces, our algorithm is able to accomplish real-time lane changing tasks in a realistic driving simulator. We compare our algorithm's lane changing performance in dense traffic with a state-of-the-art autonomous lane changing algorithm to show the advantage of iterative reasoning and active learning in terms of avoiding overly conservative behaviors and achieving the driving objective successfully.

Autonomous vehicles (AVs) must share the driving space with other drivers and often employ conservative motion planning strategies to ensure safety. These conservative strategies can negatively impact AV's performance and significantly slow traffic throughput. Therefore, to avoid conservatism, we design an interaction-aware motion planner for the ego vehicle (AV) that interacts with surrounding vehicles to perform complex maneuvers in a locally optimal manner. Our planner uses a neural network-based interactive trajectory predictor and analytically integrates it with model predictive control (MPC). We solve the MPC optimization using the alternating direction method of multipliers (ADMM) and prove the algorithm's convergence. We provide an empirical study and compare our method with a baseline heuristic method.

Deep reinforcement learning (DRL) provides a promising way for intelligent agents (e.g., autonomous vehicles) to learn to navigate complex scenarios. However, DRL with neural networks as function approximators is typically considered a black box with little explainability and often suffers from suboptimal performance, especially for autonomous navigation in highly interactive multi-agent environments. To address these issues, we propose three auxiliary tasks with spatio-temporal relational reasoning and integrate them into the standard DRL framework, which improves the decision making performance and provides explainable intermediate indicators. We propose to explicitly infer the internal states (i.e., traits and intentions) of surrounding agents (e.g., human drivers) as well as to predict their future trajectories in the situations with and without the ego agent through counterfactual reasoning. These auxiliary tasks provide additional supervision signals to infer the behavior patterns of other interactive agents. Multiple variants of framework integration strategies are compared. We also employ a spatio-temporal graph neural network to encode relations between dynamic entities, which enhances both internal state inference and decision making of the ego agent. Moreover, we propose an interactivity estimation mechanism based on the difference between predicted trajectories in these two situations, which indicates the degree of influence of the ego agent on other agents. To validate the proposed method, we design an intersection driving simulator based on the Intelligent Intersection Driver Model (IIDM) that simulates vehicles and pedestrians. Our approach achieves robust and state-of-the-art performance in terms of standard evaluation metrics and provides explainable intermediate indicators (i.e., internal states, and interactivity scores) for decision making., Comment: 18 pages, 14 figures

We propose a risk-aware crash mitigation system (RCMS), to augment any existing motion planner (MP), that enables an autonomous vehicle to perform evasive maneuvers in high-risk situations and minimize the severity of collision if a crash is inevitable. In order to facilitate a smooth transition between RCMS and MP, we develop a novel activation mechanism that combines instantaneous as well as predictive collision risk evaluation strategies in a unified hysteresis-band approach. For trajectory planning, we deploy a modular receding horizon optimization-based approach that minimizes a smooth situational risk profile, while adhering to the physical road limits as well as vehicular actuator limits. We demonstrate the performance of our approach in a simulation environment., Comment: Presented at the 26th IEEE International Conference on Intelligent Transportation Systems (ITSC) 2023, Bilbao, Bizkaia, Spain

Although deep reinforcement learning (DRL) has shown promising results for autonomous navigation in interactive traffic scenarios, existing work typically adopts a fixed behavior policy to control social vehicles in the training environment. This may cause the learned driving policy to overfit the environment, making it difficult to interact well with vehicles with different, unseen behaviors. In this work, we introduce an efficient method to train diverse driving policies for social vehicles as a single meta-policy. By randomizing the interaction-based reward functions of social vehicles, we can generate diverse objectives and efficiently train the meta-policy through guiding policies that achieve specific objectives. We further propose a training strategy to enhance the robustness of the ego vehicle's driving policy using the environment where social vehicles are controlled by the learned meta-policy. Our method successfully learns an ego driving policy that generalizes well to unseen situations with out-of-distribution (OOD) social agents' behaviors in a challenging uncontrolled T-intersection scenario., Comment: ITSC 2023

Multi-agent reinforcement learning (MARL) provides an efficient way for simultaneously learning policies for multiple agents interacting with each other. However, in scenarios requiring complex interactions, existing algorithms can suffer from an inability to accurately anticipate the influence of self-actions on other agents. Incorporating an ability to reason about other agents' potential responses can allow an agent to formulate more effective strategies. This paper adopts a recursive reasoning model in a centralized-training-decentralized-execution framework to help learning agents better cooperate with or compete against others. The proposed algorithm, referred to as the Recursive Reasoning Graph (R2G), shows state-of-the-art performance on multiple multi-agent particle and robotics games., Comment: AAAI 2022

It can be difficult to autonomously produce driver behavior so that it appears natural to other traffic participants. Through Inverse Reinforcement Learning (IRL), we can automate this process by learning the underlying reward function from human demonstrations. We propose a new IRL algorithm that learns a goal-conditioned spatiotemporal reward function. The resulting costmap is used by Model Predictive Controllers (MPCs) to perform a task without any hand-designing or hand-tuning of the cost function. We evaluate our proposed Goal-conditioned SpatioTemporal Zeroing Maximum Entropy Deep IRL (GSTZ)-MEDIRL framework together with MPC in the CARLA simulator for autonomous driving, lane keeping, and lane changing tasks in a challenging dense traffic highway scenario. Our proposed methods show higher success rates compared to other baseline methods including behavior cloning, state-of-the-art RL policies, and MPC with a learning-based behavior prediction model., Comment: IEEE Robotics and Automation Letters (RA-L)

A human-centered robot needs to reason about the cognitive limitation and potential irrationality of its human partner to achieve seamless interactions. This paper proposes an anytime game-theoretic planner that integrates iterative reasoning models, a partially observable Markov decision process, and chance-constrained Monte-Carlo belief tree search for robot behavioral planning. Our planner enables a robot to safely and actively reason about its human partner's latent cognitive states (bounded intelligence and irrationality) in real-time to maximize its utility better. We validate our approach in an autonomous driving domain where our behavioral planner and a low-level motion controller hierarchically control an autonomous car to negotiate traffic merges. Simulations and user studies are conducted to show our planner's effectiveness., Comment: Presented at ICRA 2021

This paper proposes a discretionary lane selection algorithm. In particular, highway driving is considered as a targeted scenario, where each lane has a different level of traffic flow. When lane-changing is discretionary, it is advised not to change lanes unless highly beneficial, e.g., reducing travel time significantly or securing higher safety. Evaluating such "benefit" is a challenge, along with multiple surrounding vehicles in dynamic speed and heading with uncertainty. We propose a real-time lane-selection algorithm with careful cost considerations and with modularity in design. The algorithm is a search-based optimization method that evaluates uncertain dynamic positions of other vehicles under a continuous time and space domain. For demonstration, we incorporate a state-of-the-art motion planner framework (Neural Networks integrated Model Predictive Control) under a CARLA simulation environment., Comment: Submitted to 32nd IEEE Intelligent Vehicles Symposium

Maneuvering in dense traffic is a challenging task for autonomous vehicles because it requires reasoning about the stochastic behaviors of many other participants. In addition, the agent must achieve the maneuver within a limited time and distance. In this work, we propose a combination of reinforcement learning and game theory to learn merging behaviors. We design a training curriculum for a reinforcement learning agent using the concept of level-$k$ behavior. This approach exposes the agent to a broad variety of behaviors during training, which promotes learning policies that are robust to model discrepancies. We show that our approach learns more efficient policies than traditional training methods., Comment: 6pages, 5 figures

Deep reinforcement learning (DRL) provides a promising way for learning navigation in complex autonomous driving scenarios. However, identifying the subtle cues that can indicate drastically different outcomes remains an open problem with designing autonomous systems that operate in human environments. In this work, we show that explicitly inferring the latent state and encoding spatial-temporal relationships in a reinforcement learning framework can help address this difficulty. We encode prior knowledge on the latent states of other drivers through a framework that combines the reinforcement learner with a supervised learner. In addition, we model the influence passing between different vehicles through graph neural networks (GNNs). The proposed framework significantly improves performance in the context of navigating T-intersections compared with state-of-the-art baseline approaches., Comment: ICRA 2021

There have been numerous advances in reinforcement learning, but the typically unconstrained exploration of the learning process prevents the adoption of these methods in many safety critical applications. Recent work in safe reinforcement learning uses idealized models to achieve their guarantees, but these models do not easily accommodate the stochasticity or high-dimensionality of real world systems. We investigate how prediction provides a general and intuitive framework to constraint exploration, and show how it can be used to safely learn intersection handling behaviors on an autonomous vehicle.

In a multi-agent setting, the optimal policy of a single agent is largely dependent on the behavior of other agents. We investigate the problem of multi-agent reinforcement learning, focusing on decentralized learning in non-stationary domains for mobile robot navigation. We identify a cause for the difficulty in training non-stationary policies: mutual adaptation to sub-optimal behaviors, and we use this to motivate a curriculum-based strategy for learning interactive policies. The curriculum has two stages. First, the agent leverages policy gradient algorithms to learn a policy that is capable of achieving multiple goals. Second, the agent learns a modifier policy to learn how to interact with other agents in a multi-agent setting. We evaluated our approach on both an autonomous driving lane-change domain and a robot navigation domain.

Dense urban traffic environments can produce situations where accurate prediction and dynamic models are insufficient for successful autonomous vehicle motion planning. We investigate how an autonomous agent can safely negotiate with other traffic participants, enabling the agent to handle potential deadlocks. Specifically we consider merges where the gap between cars is smaller than the size of the ego vehicle. We propose a game theoretic framework capable of generating and responding to interactive behaviors. Our main contribution is to show how game-tree decision making can be executed by an autonomous vehicle, including approximations and reasoning that make the tree-search computationally tractable. Additionally, to test our model we develop a stochastic rule-based traffic agent capable of generating interactive behaviors that can be used as a benchmark for simulating traffic participants in a crowded merge setting.

Estimating statistical uncertainties allows autonomous agents to communicate their confidence during task execution and is important for applications in safety-critical domains such as autonomous driving. In this work, we present the uncertainty-aware imitation learning (UAIL) algorithm for improving end-to-end control systems via data aggregation. UAIL applies Monte Carlo Dropout to estimate uncertainty in the control output of end-to-end systems, using states where it is uncertain to selectively acquire new training data. In contrast to prior data aggregation algorithms that force human experts to visit sub-optimal states at random, UAIL can anticipate its own mistakes and switch control to the expert in order to prevent visiting a series of sub-optimal states. Our experimental results from simulated driving tasks demonstrate that our proposed uncertainty estimation method can be leveraged to reliably predict infractions. Our analysis shows that UAIL outperforms existing data aggregation algorithms on a series of benchmark tasks., Comment: Accepted to International Conference on Robotics and Automation 2019

Machine learning has shown tremendous growth in the past decades, unlocking new capabilities in a variety of fields including computer vision, natural language processing, and robotic control. While the sophistication of individual problems a learning system can handle has greatly advanced, the ability of a system to extend beyond an individual problem to adapt and solve new problems has progressed more slowly. This thesis explores the problem of progressive learning. The goal is to develop methodologies that accumulate, transfer, and adapt knowledge in applied settings where the system is faced with the ambiguity and resource limitations of operating in the physical world. There are undoubtedly many challenges to designing such a system, my thesis looks at the component of this problem related to how knowledge from previous tasks can be a benefit in the domain of reinforcement learning where the agent receives rewards for positive actions. Reinforcement learning is particularly difficult when training on physical systems, like mobile robots, where repeated trials can damage the system and unrestricted exploration is often associated with safety risks. I investigate how knowledge can be efficiently accumulated and applied to future reinforcement learning problems on mobile robots in order to reduce sample complexity and enable systems to adapt to novel settings. Doing this involves mathematical models which can combine knowledge from multiple tasks, methods for restructuring optimizations and data collection to handle sequential updates, and data selection strategies that can be used to address resource limitations.

A variety of cooperative multi-agent control problems require agents to achieve individual goals while contributing to collective success. This multi-goal multi-agent setting poses difficulties for recent algorithms, which primarily target settings with a single global reward, due to two new challenges: efficient exploration for learning both individual goal attainment and cooperation for others' success, and credit-assignment for interactions between actions and goals of different agents. To address both challenges, we restructure the problem into a novel two-stage curriculum, in which single-agent goal attainment is learned prior to learning multi-agent cooperation, and we derive a new multi-goal multi-agent policy gradient with a credit function for localized credit assignment. We use a function augmentation scheme to bridge value and policy functions across the curriculum. The complete architecture, called CM3, learns significantly faster than direct adaptations of existing algorithms on three challenging multi-goal multi-agent problems: cooperative navigation in difficult formations, negotiating multi-vehicle lane changes in the SUMO traffic simulator, and strategic cooperation in a Checkers environment., Comment: Published at International Conference on Learning Representations 2020

Deep reinforcement learning has emerged as a powerful tool for a variety of learning tasks, however deep nets typically exhibit forgetting when learning multiple tasks in sequence. To mitigate forgetting, we propose an experience replay process that augments the standard FIFO buffer and selectively stores experiences in a long-term memory. We explore four strategies for selecting which experiences will be stored: favoring surprise, favoring reward, matching the global training distribution, and maximizing coverage of the state space. We show that distribution matching successfully prevents catastrophic forgetting, and is consistently the best approach on all domains tested. While distribution matching has better and more consistent performance, we identify one case in which coverage maximization is beneficial - when tasks that receive less trained are more important. Overall, our results show that selective experience replay, when suitable selection algorithms are employed, can prevent catastrophic forgetting., Comment: Presented in 32nd Conference on Artificial Intelligence (AAAI 2018)

Providing an efficient strategy to navigate safely through unsignaled intersections is a difficult task that requires determining the intent of other drivers. We explore the effectiveness of Deep Reinforcement Learning to handle intersection problems. Using recent advances in Deep RL, we are able to learn policies that surpass the performance of a commonly-used heuristic approach in several metrics including task completion time and goal success rate and have limited ability to generalize. We then explore a system's ability to learn active sensing behaviors to enable navigating safely in the case of occlusions. Our analysis, provides insight into the intersection handling problem, the solutions learned by the network point out several shortcomings of current rule-based methods, and the failures of our current deep reinforcement learning system point to future research directions., Comment: IEEE International Conference on Robotics and Automation (ICRA 2018)

We analyze how the knowledge to autonomously handle one type of intersection, represented as a Deep Q-Network, translates to other types of intersections (tasks). We view intersection handling as a deep reinforcement learning problem, which approximates the state action Q function as a deep neural network. Using a traffic simulator, we show that directly copying a network trained for one type of intersection to another type of intersection decreases the success rate. We also show that when a network that is pre-trained on Task A and then is fine-tuned on a Task B, the resulting network not only performs better on the Task B than an network exclusively trained on Task A, but also retained knowledge on the Task A. Finally, we examine a lifelong learning setting, where we train a single network on five different types of intersections sequentially and show that the resulting network exhibited catastrophic forgetting of knowledge on previous tasks. This result suggests a need for a long-term memory component to preserve knowledge., Comment: Submitted to IEEE International Conference on Intelligent Transportation Systems (ITSC 2017)

Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong learning settings where the goal is to learn each consecutive task rapidly from as little data as possible. To reduce this burden, we develop a lifelong learning method based on coupled dictionary learning that utilizes high-level task descriptions to model the inter-task relationships. We show that using task descriptors improves the performance of the learned task policies, providing both theoretical justification for the benefit and empirical demonstration of the improvement across a variety of learning problems. Given only the descriptor for a new task, the lifelong learner is also able to accurately predict a model for the new task through zero-shot learning using the coupled dictionary, eliminating the need to gather training data before addressing the task., Comment: 28 pages

We view intersection handling on autonomous vehicles as a reinforcement learning problem, and study its behavior in a transfer learning setting. We show that a network trained on one type of intersection generally is not able to generalize to other intersections. However, a network that is pre-trained on one intersection and fine-tuned on another performs better on the new task compared to training in isolation. This network also retains knowledge of the prior task, even though some forgetting occurs. Finally, we show that the benefits of fine-tuning hold when transferring simulated intersection handling knowledge to a real autonomous vehicle., Comment: Appeared in Lifelong Learning Workshop @ ICML 2017. arXiv admin note: text overlap with arXiv:1705.01197