Solving Reach-Avoid-Stay Problems Using Deep Deterministic Policy Gradients

Reach-Avoid-Stay (RAS) optimal control enables systems such as robots and air taxis to reach their targets, avoid obstacles, and stay near the target. However, current methods for RAS often struggle with handling complex, dynamic environments and scaling to high-dimensional systems. While reinforcement learning (RL)-based reachability analysis addresses these challenges, it has yet to tackle the RAS problem. In this paper, we propose a two-step deep deterministic policy gradient (DDPG) method to extend RL-based reachability method to solve RAS problems. First, we train a function that characterizes the maximal robust control invariant set within the target set, where the system can safely stay, along with its corresponding policy. Second, we train a function that defines the set of states capable of safely reaching the robust control invariant set, along with its corresponding policy. We prove that this method results in the maximal robust RAS set in the absence of training errors and demonstrate that it enables RAS in complex environments, scales to high-dimensional systems, and achieves higher success rates for the RAS task compared to previous methods, validated through one simulation and two high-dimensional experiments.

Don't Get Stuck: A Deadlock Recovery Approach

When multiple agents share space, interactions can lead to deadlocks, where no agent can advance towards its goal. This paper addresses this challenge with a deadlock recovery strategy. In particular, the proposed algorithm integrates hybrid-A$^\star$, STL, and MPPI frameworks. Specifically, hybrid-A$^\star$ generates a reference path, STL defines a goal (deadlock avoidance) and associated constraints (w.r.t. traffic rules), and MPPI refines the path and speed accordingly. This STL-MPPI framework ensures system compliance to specifications and dynamics while ensuring the safety of the resulting maneuvers, indicating a strong potential for application to complex traffic scenarios (and rules) in practice. Validation studies are conducted in simulations and on scaled cars, respectively, to demonstrate the effectiveness of the proposed algorithm.

Gaussian Lane Keeping: A Robust Prediction Baseline

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.

Adaptive Prediction Ensemble: Improving Out-of-Distribution Generalization of Motion Forecasting

Deep learning-based trajectory prediction models for autonomous driving often struggle with generalization to out-of-distribution (OOD) scenarios, sometimes performing worse than simple rule-based models. To address this limitation, we propose a novel framework, Adaptive Prediction Ensemble (APE), which integrates deep learning and rule-based prediction experts. A learned routing function, trained concurrently with the deep learning model, dynamically selects the most reliable prediction based on the input scenario. Our experiments on large-scale datasets, including Waymo Open Motion Dataset (WOMD) and Argoverse, demonstrate improvement in zero-shot generalization across datasets. We show that our method outperforms individual prediction models and other variants, particularly in long-horizon prediction and scenarios with a high proportion of OOD data. This work highlights the potential of hybrid approaches for robust and generalizable motion prediction in autonomous driving.

Towards Scalable & Efficient Interaction-Aware Planning in Autonomous Vehicles using Knowledge Distillation

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.

Competition-Aware Decision-Making Approach for Mobile Robots in Racing Scenarios

This paper presents a game-theoretic strategy for racing, where the autonomous ego agent seeks to block a racing opponent that aims to overtake the ego agent. After a library of trajectory candidates and an associated reward matrix are constructed, the optimal trajectory in terms of maximizing the cumulative reward over the planning horizon is determined based on the level-K reasoning framework. In particular, the level of the opponent is estimated online according to its behavior over a past window and is then used to determine the trajectory for the ego agent. Taking into account that the opponent may change its level and strategy during the decision process of the ego agent, we introduce a trajectory mixing strategy that blends the level-K optimal trajectory with a fail-safe trajectory. The overall algorithm was tested and evaluated in various simulated racing scenarios, which also includes human-in-the-loop experiments. Comparative analysis against the conventional level-K framework demonstrates the superiority of our proposed approach in terms of overtake-blocking success rates.

Efficient and Interaction-Aware Trajectory Planning for Autonomous Vehicles with Particle Swarm Optimization

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.

Multi-Profile Quadratic Programming (MPQP) for Optimal Gap Selection and Speed Planning of Autonomous Driving

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.

RCMS: Risk-Aware Crash Mitigation System for Autonomous Vehicles

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.

SLAS: Speed and Lane Advisory System for Highway Navigation

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.