Liting Sun

• Doctor of Philosophy
• PhD Student at University of California, Berkeley

While autonomous vehicles still struggle to solve challenging situations during on-road driving, humans have long mastered the essence of driving with efficient, transferable, and adaptable driving capability. By mimicking humans' cognition model and semantic understanding during driving, we propose HATN, a hierarchical framework to generate high-q...

The core value of simulation-based autonomy tests is to create densely extreme traffic scenarios to test the performance and robustness of the algorithms and systems. Test scenarios are usually designed or extracted manually from the real-world data, which is inefficient with a remarkable domain gap compared with testing in real scenarios. Therefor...

When autonomous vehicles still struggle to solve challenging situations during on-road driving, humans have long mastered the essence of driving with efficient transferable and adaptable driving capability. By mimicking humans' cognition model and semantic understanding during driving, we present HATN, a hierarchical framework to generate high-qual...

An outstanding challenge with safety methods for human-robot interaction is reducing their conservatism while maintaining robustness to variations in human behavior. In this work, we propose that robots use confidence-aware game-theoretic models of human behavior when assessing the safety of a human-robot interaction. By treating the influence betw...

We propose an imitation learning system for autonomous driving in urban traffic with interactions. We train a Behavioral Cloning~(BC) policy to imitate driving behavior collected from the real urban traffic, and apply the data aggregation algorithm to improve its performance iteratively. Applying data aggregation in this setting comes with two chal...

Microscopic epidemic models are powerful tools for government policy makers to predict and simulate epidemic outbreaks, which can capture the impact of individual behaviors on the macroscopic phenomenon. However, existing models only consider simple rule-based individual behaviors, limiting their applicability. This paper proposes a deep-reinforcem...

Motion planning under uncertainty is of significant importance for safety-critical systems such as autonomous vehicles. Such systems have to satisfy necessary constraints (e.g., collision avoidance) with potential uncertainties coming from either disturbed system dynamics or noisy sensor measurements. However, existing motion planning methods canno...

Safety assurance is a critical yet challenging aspect when developing self-driving technologies. Hamilton-Jacobi backward-reachability analysis is a formal verification tool for verifying the safety of dynamic systems in the presence of disturbances. However, the standard approach is too conservative to be applied to self-driving applications due t...

Classical game-theoretic approaches for multi-agent systems in both the forward policy design problem and the inverse reward learning problem often make strong rationality assumptions: agents perfectly maximize expected utilities under uncertainties. Such assumptions, however, substantially mismatch with observed human behaviors such as satisficing...

High capacity end-to-end approaches for human motion prediction have the ability to represent subtle nuances in human behavior, but struggle with robustness to out of distribution inputs and tail events. Planning-based prediction, on the other hand, can reliably output decent-but-not-great predictions: it is much more stable in the face of distribu...

Reward function, as an incentive representation that recognizes humans' agency and rationalizes humans' actions, is particularly appealing for modeling human behavior in human-robot interaction. Inverse Reinforcement Learning is an effective way to retrieve reward functions from demonstrations. However, it has always been challenging when applying...

Generating diverse and comprehensive interacting agents to evaluate the decision-making modules of autonomous vehicles~(AV) is essential for safe and robust planning. Due to efficiency and safety concerns, most researchers choose to train adversary agents in simulators and generate test cases to interact with evaluated AVs. However, most existing m...

Autonomous vehicles (AVs) need to share the road with multiple, heterogeneous road users in a variety of driving scenarios. It is overwhelming and unnecessary to carefully interact with all observed agents, and AVs need to determine whether and when to interact with each surrounding agent. In order to facilitate the design and testing of predic...

Many manipulation tasks require robots to interact with unknown environments. In such applications, the ability to adapt the impedance according to different task phases and environment constraints is crucial for safety and performance. Although many approaches based on deep reinforcement learning (RL) and learning from demonstration (LfD) have bee...

As more and more autonomous vehicles (AVs) are being deployed on public roads, designing socially compatible behaviors for them is important. In order to generate safe and efficient actions, AVs need to not only predict the future behaviors of other traffic participants, but also be aware of the uncertainties associated with such behavior predictio...

In this paper, a practical fractional-order variablegain super-twisting algorithm (PFVSTA) is proposed to improve the tracking performance of wafer stages for semiconductor manufacturing. Based on sliding mode control (SMC), the proposed PFVSTA enhances the tracking performance from three aspects: 1) alleviating the chattering phenomenon via super-...

Many manipulation tasks require robots to interact with unknown environments. In such applications, the ability to adapt the impedance according to different task phases and environment constraints is crucial for safety and performance. Although many approaches based on deep reinforcement learning (RL) and learning from demonstration (LfD) have bee...

In this paper, a practical fractional-order variable-gain super-twisting algorithm (PFVSTA) is proposed to improve the tracking performance of wafer stages for semiconductor manufacturing. Based on the sliding mode control (SMC), the proposed PFVSTA enhances the tracking performance from three aspects: 1) alleviating the chattering phenomenon via s...

The precise motion control of a multi-degree of freedom~(DOF) robot manipulator is always challenging due to its nonlinear dynamics, disturbances, and uncertainties. Because most manipulators are controlled by digital signals, a novel higher-order sliding mode controller in the discrete-time form with time delay estimation is proposed in this paper...

When robots work with humans for collaborative task, they need to plan their actions while taking humans' actions into account. However, due to the complexity of the tasks and stochastic nature of human collaborators, it is quite challenging for the robot to efficiently collaborate with the humans. To address this challenge, in this paper, we first...

To obtain precise motion control of wafer stages, an adaptive neural network and fractional-order super-twisting control strategy is proposed. Based on sliding mode control (SMC), the proposed controller aims to address two challenges in SMC: 1) reducing the chattering phenomenon, and 2) attenuating the influence of model uncertainties and disturba...

Autonomous vehicles need to handle various traffic conditions and make safe and efficient decisions and maneuvers. However, on the one hand, a single optimization/sampling-based motion planner cannot efficiently generate safe trajectories in real time, particularly when there are many interactive vehicles near by. On the other hand, end-to-end lear...

Autonomous vehicles (AVs) need to interact with other traffic participants who can be either cooperative or aggressive, attentive or inattentive. Such different characteristics can lead to quite different interactive behaviors. Hence, to achieve safe and efficient autonomous driving, AVs need to be aware of such uncertainties when they plan their o...

Zero phase error tracking (ZPET) control has gained popularity as a simple yet effective feedforward control method for tracking time varying desired trajectories by the plant output. In this paper, we will show that the zero-order hold equivalent of continuous time transfer function, i.e. pulse transfer function, naturally has a property to realiz...

Classical game-theoretic approaches for multi-agent systems in both the forward policy design problem and the inverse reward learning problem often make strong rationality assumptions: agents perfectly maximize expected utilities under uncertainties. Such assumptions, however, substantially mismatch with observed humans’ behaviors such as satisficin...

Safety is an important topic in autonomous driving since any collision may cause serious damage to people and the environment. Hamilton-Jacobi (HJ) Reachability is a formal method that verifies safety in multi-agent interaction and provides a safety controller for collision avoidance. However, due to the worst-case assumption on the car's future ac...

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, partially observable Markov decision process, and chance-constrained Monte-Carlo belief tree search...

Autonomous vehicles (AVs) need to share the road with multiple, heterogeneous road users in a variety of driving scenarios. It is overwhelming and unnecessary to carefully interact with all observed agents, and AVs need to determine whether and when to interact with each surrounding agent. In order to facilitate the design and testing of prediction...

As more and more autonomous vehicles (AVs) are being deployed on public roads, designing socially compatible behaviors for them is of critical importance. Based on observations, AVs need to predict the future behaviors of other traffic participants, and be aware of the uncertainties associated with such prediction so that safe, efficient, and human...

Autonomous vehicles (AVs) need to interact with other traffic participants who can be either cooperative or aggressive, attentive or inattentive. Such different characteristics can lead to quite different interactive behaviors. Hence, to achieve safe and efficient autonomous driving, AVs need to be aware of such uncertainties when they plan their o...

Autonomous driving planning is a challenging problem when the environment is complicated. It is difficult for the planner to find a good trajectory that navigates autonomous cars safely with crowded surrounding vehicles. To solve this complicated problem, a fast algorithm that generates a high-quality, safe trajectory is necessary. Constrained Iter...

In human-robot interaction (HRI) systems, such as autonomous vehicles, understanding and representing human behavior are important. Human behavior is naturally rich and diverse. Cost/reward learning, as an efficient way to learn and represent human behavior, has been successfully applied in many domains. Most of traditional inverse reinforcement le...

In this paper, a novel fractional-order variable-gain super-twisting control (FVSTC) scheme is proposed and applied to improve the tracking performance of wafer stages in the photolithography systems. The FVSTC overcomes the drawbacks of the super-twisting control (STC) such as slow response speed and incomplete compensation to disturbances. First,...

In the past decades, we have witnessed significant progress in the domain of autonomous driving. Advanced techniques based on optimization and reinforcement learning become increasingly powerful when solving the forward problem: given designed reward/cost functions, how we should optimize them and obtain driving policies that interact with the envi...

In the past decades, we have witnessed significant progress in the domain of autonomous driving. Advanced techniques based on optimization and reinforcement learning (RL) become increasingly powerful at solving the forward problem: given designed reward/cost functions, how should we optimize them and obtain driving policies that interact with the e...

Human-robot collaboration (HRC) is becoming increasingly important as the paradigm of manufacturing is shifting from mass production to mass customization. The introduction of HRC can significantly improve the flexibility and intelligence of automation. To efficiently finish tasks in HRC systems, the robots need to not only predict the future movem...

Human motion prediction is non-trivial in modern industrial settings. Accurate prediction of human motion can not only improve efficiency in human robot collaboration, but also enhance human safety in close proximity to robots. Among existing prediction models, the parameterization and identification methods of those models vary. It remains unclear...

To obtain precise motion control of wafer stages, an adaptive neural network and fractional-order super-twisting control strategy is proposed. Based on sliding mode control (SMC), the proposed controller aims to address two challenges in SMC: 1) reducing the chattering phenomenon, and 2) attenuating the influence of model uncertainties and disturba...

Sampling-based motion planning methods are widely adopted in autonomous driving. Typically, sampling can be decoupled into two layers: a path sampling layer and a speed profile sampling layer. For the path sampling layer, traditional methods tend to sample with a uniform distribution over the whole feasible space, which might cause either computati...

Simulation has long been an essential part of testing autonomous driving systems, but only recently has simulation been useful for building and training self-driving vehicles. Vehicle behavioural models are necessary to simulate the interactions between robot cars. This paper proposed a new method to formalize the lane-changing model in urban drivi...

Behavior-related research areas such as motion prediction/planning, representation/imitation learning, behavior modeling/generation, and algorithm testing, require support from high-quality motion datasets containing interactive driving scenarios with different driving cultures. In this paper, we present an INTERnational, Adversarial and Cooperativ...

Interactive motion datasets of road participants are vital to the development of autonomous vehicles in both industry and academia. Research areas such as motion prediction, motion planning, representation learning, imitation learning, behavior modeling, behavior generation, and algorithm testing, require support from high-quality motion datasets c...

Closed-loop disturbance rejection without sacrificing overall system performance is a fundamental issue in a wide range of applications from precision motion control, active noise cancellation, to advanced manufacturing. The core of rejecting band-limited disturbances is the shaping of feedback loops to actively and flexibly respond to different di...

Iterative learning control (ILC) has been well recognized for its ability to improve the tracking performance of systems that perform repetitive tasks. Its achievable performance, however, can be significantly degraded by the presence of non-repetitive disturbances which vary every iteration. Such may be a case for high-precision robot manipulators...

Understanding human driving behavior is important for autonomous vehicles. In this paper, we propose an interpretable human behavior model in interactive driving scenarios based on the cumulative prospect theory (CPT). As a non-expected utility theory, CPT can well explain some systematically biased or "irrational" behavior/decisions of human that...

Accurately predicting future behaviors of surrounding vehicles is an essential capability for autonomous vehicles in order to plan safe and feasible trajectories. The behaviors of others, however, are full of uncertainties. Both rational and irrational behaviors exist, and the autonomous vehicles need to be aware of this in their prediction module....

In general, it is not intuitive to quantify the performance of nonlinear systems; thus, designing controllers and/or estimators is not easy. Moreover, there are situations, in which a system designed with a fixed feedback controller is not customizable, and yet its closed-loop performance (e.g., disturbance attenuation) is not satisfactory. In this...

Understanding human driving behavior is important for autonomous vehicles. In this paper, we propose an interpretable human behavior model in interactive driving scenarios based on the cumulative prospect theory (CPT). As a non-expected utility theory, CPT can well explain some systematically biased or ``irrational'' behavior/decisions of human tha...

Autonomous cars have to navigate in dynamic environment which can be full of uncertainties. The uncertainties can come either from sensor limitations such as occlusions and limited sensor range, or from probabilistic prediction of other road participants, or from unknown social behavior in a new area. To safely and efficiently drive in the presence...

Human robot collaboration (HRC) is becoming increasingly important as the paradigm of manufacturing is shifting from mass production to mass customization. The introduction of HRC can significantly improve the flexibility and intelligence of automation. However, due to the stochastic and time-varying nature of human collaborators, it is challenging...

Most existing methods rely on the torque information of a servo drive to predict the tracking error caused by the friction force (friction error), but the torque information is not available in certain systems. This paper proposes a position-based modeling method for the friction error. Two examples are given to verify the practicality of the propo...

Iterative learning control (ILC) has been well recognized for its ability to improve the tracking performance of systems that perform repetitive tasks. Its achievable performance, however, can be significantly degraded by the presence of non-repetitive disturbances which vary every iteration. Such may be a case for high-precision robot manipulators...

Safety and efficiency are two key elements for planning and control in autonomous driving. Theoretically, model-based optimization methods, such as Model Predictive Control (MPC), can provide such optimal driving policies. Their computational complexity, however, grows exponentially with horizon length and number of surrounding vehicles. This makes...

Autonomous vehicles should be able to generate accurate probabilistic predictions for uncertain behavior of other road users. Moreover, reactive predictions are necessary in highly interactive driving scenarios to answer "what if I take this action in the future" for autonomous vehicles. There is no existing unified framework to homogenize the prob...

Autonomous vehicles (AVs) are on the road. To safely and efficiently interact with other road participants, AVs have to accurately predict the behavior of surrounding vehicles and plan accordingly. Such prediction should be probabilistic, to address the uncertainties in human behavior. Such prediction should also be interactive, since the distribut...

In precision motion systems, suppression of high-frequency unknown disturbances is always critical and challenging. This becomes even more difficult when the system output is only available at limited sampling rates, but the frequencies of the disturbances are beyond the Nyquist frequency of the output samplers. Under such scenarios, the un-availab...

Typically, autonomous cars optimize for a combination of safety, efficiency, and driving quality. But as we get better at this optimization, we start seeing behavior go from too conservative to too aggressive. The car's behavior exposes the incentives we provide in its cost function. In this work, we argue for cars that are not optimizing a purely...

Iterative learning control (ILC) is an effective technique that improves the tracking performance of systems by adjusting the feedforward control signal based on the memory data. The key in ILC is to design learning filters with guaranteed convergence and robustness, which usually involves lots of tuning effort especially in high-order ILC. To faci...

For safe and efficient planning and control in autonomous driving, we need a driving policy which can achieve desirable driving quality in long-term horizon with guaranteed safety and feasibility. Optimization-based approaches, such as Model Predictive Control (MPC), can provide such optimal policies, but their computational complexity is generally...

In building temperature control, one of the main challenges is to maintain good performance in the presence of disturbances from both outdoor weather and indoor human activities. Considering the fact that such disturbances contain both repetitive patterns and non-repetitive uncertainties, this paper proposes a two-degree-of-freedom (2-DOF) iterativ...

In digital/sampled-data motion control systems, the system outputs are only available at certain rates. This sets a great challenge to high-precision motion control systems that subject to high-frequency disturbances, since the feedback regulator cannot directly observe the inter-sample outputs. To handle such situations, a robust multirate control...

Modern hard disk drive (HDD) systems are subjected to various external disturbances. One particular category, defined as wide-band disturbances, can generate vibrations with their energy highly concentrated at several frequency bands. Such vibrations are commonly time-varying and strongly environment/product-dependent; and the wide spectral peaks c...

Iterative learning control (ILC) is an effective technique to improve the tracking performance of systems through adjusting the feedforward control signal based on the memory data. It is critically important to design the learning filters in the ILC algorithm that assures the robust stability of the convergence of tracking errors from one iteration...

Nyquist frequency limits the frequency range of the continuous-time signals that can be reconstructed through the sampled discrete-time signals. In hard disk drives (HDDs), there exist resonance modes near and beyond the Nyquist frequency in the voice coil motor (VCM). Such resonance modes, if excited, may generate vibration beyond the Nyquist freq...

Iterative learning control (ILC) is an effective control technique for servo improvement in systems that repetitively execute the same tasks. In the learning process, the measured tracking error from the current iteration is incorporated to generate a new feedforward compensation signal to improve the system performance in the next iteration. Due t...

In this paper, an optimization-based constrained iterative learning control (ILC) with an iteratively tunable feedback controller is proposed for building temperature control systems. To guarantee good control performance in the presence of both repetitive and non-repetitive disturbances, the ILC input and the feedback controller are optimized simu...