Search

Predicting agents' behavior for vehicles and pedestrians is challenging due to a myriad of factors including the uncertainty attached to different intentions, inter-agent interactions, traffic (environment) rules, individual inclinations, and agent dynamics. Consequently, a plethora of neural network-driven prediction models have been introduced in the literature to encompass these intricacies to accurately predict the agent behavior. Nevertheless, many of these approaches falter when confronted with scenarios beyond their training datasets, and lack interpretability, raising concerns about their suitability for real-world applications such as autonomous driving. Moreover, these models frequently demand additional training, substantial computational resources, or specific input features necessitating extensive implementation endeavors. In response, we propose Gaussian Lane Keeping (GLK), a robust prediction method for autonomous vehicles that can provide a solid baseline for comparison when developing new algorithms and a sanity check for real-world deployment. We provide several extensions to the GLK model, evaluate it on the CitySim dataset, and show that it outperforms the neural-network based predictions.

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.

In the context of human-supervised autonomy, we study the problem of optimal fidelity selection for a human operator performing an underwater visual search task. Human performance depends on various cognitive factors such as workload and fatigue. We perform human experiments in which participants perform two tasks simultaneously: a primary task, which is subject to evaluation, and a secondary task to estimate their workload. The primary task requires participants to search for underwater mines in videos, while the secondary task involves a simple visual test where they respond when a green light displayed on the side of their screens turns red. Videos arrive as a Poisson process and are stacked in a queue to be serviced by the human operator. The operator can choose to watch the video with either normal or high fidelity, with normal fidelity videos playing at three times the speed of high fidelity ones. Participants receive rewards for their accuracy in mine detection for each primary task and penalties based on the number of videos waiting in the queue. We consider the workload of the operator as a hidden state and model the workload dynamics as an Input-Output Hidden Markov Model (IOHMM). We use a Partially Observable Markov Decision Process (POMDP) to learn an optimal fidelity selection policy, where the objective is to maximize total rewards. Our results demonstrate improved performance when videos are serviced based on the optimal fidelity policy compared to a baseline where humans choose the fidelity level themselves.

Cognitive rehabilitation, STEM (science, technology, engineering, and math) skill acquisition, and coaching games such as chess often require tutoring decision-making strategies. The advancement of AI-driven tutoring systems for facilitating human learning requires an understanding of the impact of evaluative feedback on human decision-making and skill development. To this end, we conduct human experiments using Amazon Mechanical Turk to study the influence of evaluative feedback on human decision-making in sequential tasks. In these experiments, participants solve the Tower of Hanoi puzzle and receive AI-generated feedback while solving it. We examine how this feedback affects their learning and skill transfer to related tasks. Additionally, treating humans as noisy optimal agents, we employ maximum entropy inverse reinforcement learning to analyze the effect of feedback on the implicit human reward structure that guides their decision making. Lastly, we explore various computational models to understand how people incorporate evaluative feedback into their decision-making processes. Our findings underscore that humans perceive evaluative feedback as indicative of their long-term strategic success, thus aiding in skill acquisition and transfer in sequential decision-making tasks. Moreover, we demonstrate that evaluative feedback fosters a more structured and organized learning experience compared to learning without feedback. Furthermore, our results indicate that providing intermediate goals alone does not significantly enhance human learning outcomes.

The two-time scale nature of SAC, which is an actor-critic algorithm, is characterised by the fact that the critic estimate has not converged for the actor at any given time, but since the critic learns faster than the actor, it ensures eventual consistency between the two. Various strategies have been introduced in literature to learn better gradient estimates to help achieve better convergence. Since gradient estimates depend upon the critic, we posit that improving the critic can provide a better gradient estimate for the actor at each time. Utilizing this, we propose Soft Actor Retrospective Critic (SARC), where we augment the SAC critic loss with another loss term - retrospective loss - leading to faster critic convergence and consequently, better policy gradient estimates for the actor. An existing implementation of SAC can be easily adapted to SARC with minimal modifications. Through extensive experimentation and analysis, we show that SARC provides consistent improvement over SAC on benchmark environments. We plan to open-source the code and all experiment data at: https://github.com/sukritiverma1996/SARC., Comment: Accepted at RLDM 2022

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.

We propose Deterministic Sequencing of Exploration and Exploitation (DSEE) algorithm with interleaving exploration and exploitation epochs for model-based RL problems that aim to simultaneously learn the system model, i.e., a Markov decision process (MDP), and the associated optimal policy. During exploration, DSEE explores the environment and updates the estimates for expected reward and transition probabilities. During exploitation, the latest estimates of the expected reward and transition probabilities are used to obtain a robust policy with high probability. We design the lengths of the exploration and exploitation epochs such that the cumulative regret grows as a sub-linear function of time.

We study optimal fidelity selection for a human operator servicing a queue of homogeneous tasks. The agent can service a task with a normal or high fidelity level, where fidelity refers to the degree of exactness and precision while servicing the task. Therefore, high-fidelity servicing results in higher-quality service but leads to larger service times and increased operator tiredness. We treat the human cognitive state as a lumped parameter that captures psychological factors such as workload and fatigue. The operator's service time distribution depends on her cognitive dynamics and the fidelity level selected for servicing the task. Her cognitive dynamics evolve as a Markov chain in which the cognitive state increases with high probability whenever she is busy and decreases while resting. The tasks arrive according to a Poisson process and the operator is penalized at a fixed rate for each task waiting in the queue. We address the trade-off between high-quality service of the task and consequent penalty due to a subsequent increase in queue length using a discrete-time Semi-Markov Decision Process framework. We numerically determine an optimal policy and the corresponding optimal value function. Finally, we establish the structural properties of an optimal fidelity policy and provide conditions under which the optimal policy is a threshold-based policy.

Explaining the behavior of black box machine learning models through human interpretable rules is an important research area. Recent work has focused on explaining model behavior locally i.e. for specific predictions as well as globally across the fields of vision, natural language, reinforcement learning and data science. We present a novel model-agnostic approach that derives rules to globally explain the behavior of classification models trained on numerical and/or categorical data. Our approach builds on top of existing local model explanation methods to extract conditions important for explaining model behavior for specific instances followed by an evolutionary algorithm that optimizes an information theory based fitness function to construct rules that explain global model behavior. We show how our approach outperforms existing approaches on a variety of datasets. Further, we introduce a parameter to evaluate the quality of interpretation under the scenario of distributional shift. This parameter evaluates how well the interpretation can predict model behavior for previously unseen data distributions. We show how existing approaches for interpreting models globally lack distributional robustness. Finally, we show how the quality of the interpretation can be improved under the scenario of distributional shift by adding out of distribution samples to the dataset used to learn the interpretation and thereby, increase robustness. All of the datasets used in our paper are open and publicly available. Our approach has been deployed in a leading digital marketing suite of products.