This paper presents a multi-agent reinforcement learning (MARL) framework for cooperative collision avoidance of UAV swarms leveraging domain knowledge-driven reward. The reward is derived from knowledge in the domain of image processing, approximating contours on a two-dimensional field. By modeling obstacles as maxima on the field, collisions are inherently avoided as contours never go through peaks or intersect. Additionally, counters are smooth and energy-efficient. Our framework enables training with large swarm sizes as the agent interaction is minimized and the need for complex credit assignment schemes or observation sharing mechanisms in state-of-the-art MARL approaches are eliminated. Moreover, UAVs obtain the ability to adapt to complex environments where contours may be non-viable or non-existent through intensive training. Extensive experiments are conducted to evaluate the performances of our framework against state-of-the-art MARL algorithms.
Autonomous navigation by drones using onboard sensors combined with machine learning and computer vision algorithms is impacting a number of domains, including agriculture, logistics, and disaster management. In this paper, we examine the use of drones for assisting visually impaired people (VIPs) in navigating through outdoor urban environments. Specifically, we present a perception-based path planning system for local planning around the neighborhood of the VIP, integrated with a global planner based on GPS and maps for coarse planning. We represent the problem using a geometric formulation and propose a multi DNN based framework for obstacle avoidance of the UAV as well as the VIP. Our evaluations conducted on a drone human system in a university campus environment verifies the feasibility of our algorithms in three scenarios; when the VIP walks on a footpath, near parked vehicles, and in a crowded street.
In complex driving environments, autonomous vehicles must navigate safely. Relying on a single predicted path, as in regression-based approaches, usually does not explicitly assess the safety of the predicted trajectory. Selection-based methods address this by generating and scoring multiple trajectory candidates and predicting the safety score for each, but face optimization challenges in precisely selecting the best option from thousands of possibilities and distinguishing subtle but safety-critical differences, especially in rare or underrepresented scenarios. We propose DriveSuprim to overcome these challenges and advance the selection-based paradigm through a coarse-to-fine paradigm for progressive candidate filtering, a rotation-based augmentation method to improve robustness in out-of-distribution scenarios, and a self-distillation framework to stabilize training. DriveSuprim achieves state-of-the-art performance, reaching 93.5% PDMS in NAVSIM v1 and 87.1% EPDMS in NAVSIM v2 without extra data, demonstrating superior safetycritical capabilities, including collision avoidance and compliance with rules, while maintaining high trajectory quality in various driving scenarios.
This paper addresses the problem of trajectory optimization for unmanned aerial vehicles (UAVs) performing time-sensitive medical deliveries in urban environments. Specifically, we consider a single UAV with 3 degree-of-freedom dynamics tasked with delivering blood packages to multiple hospitals, each with a predefined time window and priority. Mission objectives are encoded using Signal Temporal Logic (STL), enabling the formal specification of spatial-temporal constraints. To ensure safety, city buildings are modeled as 3D convex obstacles, and obstacle avoidance is handled through a Convex Feasible Set (CFS) method. The entire planning problem-combining UAV dynamics, STL satisfaction, and collision avoidance-is formulated as a convex optimization problem that ensures tractability and can be solved efficiently using standard convex programming techniques. Simulation results demonstrate that the proposed method generates dynamically feasible, collision-free trajectories that satisfy temporal mission goals, providing a scalable and reliable approach for autonomous UAV-based medical logistics.
Human trajectory forecasting is crucial in applications such as autonomous driving, robotics and surveillance. Accurate forecasting requires models to consider various factors, including social interactions, multi-modal predictions, pedestrian intention and environmental context. While existing methods account for these factors, they often overlook the impact of the environment, which leads to collisions with obstacles. This paper introduces ECAM (Environmental Collision Avoidance Module), a contrastive learning-based module to enhance collision avoidance ability with the environment. The proposed module can be integrated into existing trajectory forecasting models, improving their ability to generate collision-free predictions. We evaluate our method on the ETH/UCY dataset and quantitatively and qualitatively demonstrate its collision avoidance capabilities. Our experiments show that state-of-the-art methods significantly reduce (-40/50%) the collision rate when integrated with the proposed module. The code is available at https://github.com/CVML-CFU/ECAM.
The rapid growth of the low-altitude economy has driven the widespread adoption of unmanned aerial vehicles (UAVs). This growing deployment presents new challenges for UAV trajectory planning in complex urban environments. However, existing studies often overlook key factors, such as urban airspace constraints and economic efficiency, which are essential in low-altitude economy contexts. Deep reinforcement learning (DRL) is regarded as a promising solution to these issues, while its practical adoption remains limited by low learning efficiency. To overcome this limitation, we propose a novel UAV trajectory planning framework that combines DRL with large language model (LLM) reasoning to enable safe, compliant, and economically viable path planning. Experimental results demonstrate that our method significantly outperforms existing baselines across multiple metrics, including data collection rate, collision avoidance, successful landing, regulatory compliance, and energy efficiency. These results validate the effectiveness of our approach in addressing UAV trajectory planning key challenges under constraints of the low-altitude economy networking.
This paper presents Q-ARDNS-Multi, an advanced multi-agent quantum reinforcement learning (QRL) framework that extends the ARDNS-FN-Quantum model, where Q-ARDNS-Multi stands for "Quantum Adaptive Reward-Driven Neural Simulator - Multi-Agent". It integrates quantum circuits with RY gates, meta-cognitive adaptation, and multi-agent coordination mechanisms for complex 3D environments. Q-ARDNS-Multi leverages a 2-qubit quantum circuit for action selection, a dual-memory system inspired by human cognition, a shared memory module for agent cooperation, and adaptive exploration strategies modulated by reward variance and intrinsic motivation. Evaluated in a $10 \times 10 \times 3$ GridWorld environment with two agents over 5000 episodes, Q-ARDNS-Multi achieves success rates of 99.6\% and 99.5\% for Agents 0 and 1, respectively, outperforming Multi-Agent Deep Deterministic Policy Gradient (MADDPG) and Soft Actor-Critic (SAC) in terms of success rate, stability, navigation efficiency, and collision avoidance. The framework records mean rewards of $-304.2891 \pm 756.4636$ and $-295.7622 \pm 752.7103$, averaging 210 steps to goal, demonstrating its robustness in dynamic settings. Comprehensive analyses, including learning curves, reward distributions, statistical tests, and computational efficiency evaluations, highlight the contributions of quantum circuits and meta-cognitive adaptation. By bridging quantum computing, cognitive science, and multi-agent RL, Q-ARDNS-Multi offers a scalable, human-like approach for applications in robotics, autonomous navigation, and decision-making under uncertainty.
We propose CARE (Collision Avoidance via Repulsive Estimation), a plug-and-play module that enhances the safety of vision-based navigation without requiring additional range sensors or fine-tuning of pretrained models. While recent foundation models using only RGB inputs have shown strong performance, they often fail to generalize in out-of-distribution (OOD) environments with unseen objects or variations in camera parameters (e.g., field of view, pose, or focal length). Without fine-tuning, these models may generate unsafe trajectories that lead to collisions, requiring costly data collection and retraining. CARE addresses this limitation by seamlessly integrating with any RGB-based navigation system that outputs local trajectories, dynamically adjusting them using repulsive force vectors derived from monocular depth maps. We evaluate CARE by combining it with state-of-the-art vision-based navigation models across multiple robot platforms. CARE consistently reduces collision rates (up to 100%) without sacrificing goal-reaching performance and improves collision-free travel distance by up to 10.7x in exploration tasks.
Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation across various tasks. Yet, most existing approaches remain limited in handling multiple types of constraints, such as collision avoidance and dynamic consistency, which are often treated separately or only partially considered. This paper proposes UniConFlow, a unified flow matching (FM) based framework for trajectory generation that systematically incorporates both equality and inequality constraints. UniConFlow introduces a novel prescribed-time zeroing function to enhance flexibility during the inference process, allowing the model to adapt to varying task requirements. To ensure constraint satisfaction, particularly with respect to obstacle avoidance, admissible action range, and kinodynamic consistency, the guidance inputs to the FM model are derived through a quadratic programming formulation, which enables constraint-aware generation without requiring retraining or auxiliary controllers. We conduct mobile navigation and high-dimensional manipulation tasks, demonstrating improved safety and feasibility compared to state-of-the-art constrained generative planners. Project page is available at https://uniconflow.github.io.
We initiate a formal study on the use of low-dimensional latent representations of dynamical systems for verifiable control synthesis. Our main goal is to enable the application of verification techniques -- such as Lyapunov or barrier functions -- that might otherwise be computationally prohibitive when applied directly to the full state representation. Towards this goal, we first provide dynamics-aware approximate conjugacy conditions which formalize the notion of reconstruction error necessary for systems analysis. We then utilize our conjugacy conditions to transfer the stability and invariance guarantees of a latent certificate function (e.g., a Lyapunov or barrier function) for a latent space controller back to the original system. Importantly, our analysis contains several important implications for learning latent spaces and dynamics, by highlighting the necessary geometric properties which need to be preserved by the latent space, in addition to providing concrete loss functions for dynamics reconstruction that are directly related to control design. We conclude by demonstrating the applicability of our theory to two case studies: (1) stabilization of a cartpole system, and (2) collision avoidance for a two vehicle system.
Safe and feasible trajectory planning is essential for real-world autonomous driving systems. However, existing learning-based planning methods often rely on expert demonstrations, which not only lack explicit safety awareness but also risk inheriting unsafe behaviors such as speeding from suboptimal human driving data. Inspired by the success of large language models, we propose Plan-R1, a novel two-stage trajectory planning framework that formulates trajectory planning as a sequential prediction task, guided by explicit planning principles such as safety, comfort, and traffic rule compliance. In the first stage, we train an autoregressive trajectory predictor via next motion token prediction on expert data. In the second stage, we design rule-based rewards (e.g., collision avoidance, speed limits) and fine-tune the model using Group Relative Policy Optimization (GRPO), a reinforcement learning strategy, to align its predictions with these planning principles. Experiments on the nuPlan benchmark demonstrate that our Plan-R1 significantly improves planning safety and feasibility, achieving state-of-the-art performance. Our code will be made public soon.
Oversteer, wherein a vehicle's rear tires lose traction and induce unintentional excessive yaw, poses critical safety challenges. Failing to control oversteer often leads to severe traffic accidents. Although recent autonomous driving efforts have attempted to handle oversteer through stabilizing maneuvers, the majority rely on expert-defined trajectories or assume obstacle-free environments, limiting real-world applicability. This paper introduces a novel end-to-end (E2E) autonomous driving approach that tackles oversteer control and collision avoidance simultaneously. Existing E2E techniques, including Imitation Learning (IL), Reinforcement Learning (RL), and Hybrid Learning (HL), generally require near-optimal demonstrations or extensive experience. Yet even skilled human drivers struggle to provide perfect demonstrations under oversteer, and high transition variance hinders accumulating sufficient data. Hence, we present Q-Compared Soft Actor-Critic (QC-SAC), a new HL algorithm that effectively learns from suboptimal demonstration data and adapts rapidly to new conditions. To evaluate QC-SAC, we introduce a benchmark inspired by real-world driver training: a vehicle encounters sudden oversteer on a slippery surface and must avoid randomly placed obstacles ahead. Experimental results show QC-SAC attains near-optimal driving policies, significantly surpassing state-of-the-art IL, RL, and HL baselines. Our method demonstrates the world's first safe autonomous oversteer control with obstacle avoidance.
Recent developments in autonomous driving and robotics underscore the necessity of safety-critical controllers. Control barrier functions (CBFs) are a popular method for appending safety guarantees to a general control framework, but they are notoriously difficult to generate beyond low dimensions. Existing methods often yield non-differentiable or inaccurate approximations that lack integrity, and thus fail to ensure safety. In this work, we use physics-informed neural networks (PINNs) to generate smooth approximations of CBFs by computing Hamilton-Jacobi (HJ) optimal control solutions. These reachability barrier networks (RBNs) avoid traditional dimensionality constraints and support the tuning of their conservativeness post-training through a parameterized discount term. To ensure robustness of the discounted solutions, we leverage conformal prediction methods to derive probabilistic safety guarantees for RBNs. We demonstrate that RBNs are highly accurate in low dimensions, and safer than the standard neural CBF approach in high dimensions. Namely, we showcase the RBNs in a 9D multi-vehicle collision avoidance problem where it empirically proves to be 5.5x safer and 1.9x less conservative than the neural CBFs, offering a promising method to synthesize CBFs for general nonlinear autonomous systems.
In this paper, a novel framework is presented that achieves a combined solution based on Multi-Robot Task Allocation (MRTA) and collision avoidance with respect to homogeneous measurement tasks taking place in industrial environments. The spatial clustering we propose offers to simultaneously solve the task allocation problem and deal with collision risks by cutting the workspace into distinguishable operational zones for each robot. To divide task sites and to schedule robot routes within corresponding clusters, we use K-means clustering and the 2-Opt algorithm. The presented framework shows satisfactory performance, where up to 93\% time reduction (1.24s against 17.62s) with a solution quality improvement of up to 7\% compared to the best performing method is demonstrated. Our method also completely eliminates collision points that persist in comparative methods in a most significant sense. Theoretical analysis agrees with the claim that spatial partitioning unifies the apparently disjoint tasks allocation and collision avoidance problems under conditions of many identical tasks to be distributed over sparse geographical areas. Ultimately, the findings in this work are of substantial importance for real world applications where both computational efficiency and operation free from collisions is of paramount importance.
To perform autonomous driving maneuvers, such as parallel or perpendicular parking, a vehicle requires continual speed and steering adjustments to follow a generated path. In consequence, the path's quality is a limiting factor of the vehicle maneuver's performance. While most path planning approaches include finding a collision-free route, optimal trajectory planning involves solving the best transition from initial to final states, minimizing the action over all paths permitted by a kinematic model. Here we propose a novel method based on sequential convex optimization, which permits flexible and efficient optimal trajectory generation. The objective is to achieve the fastest time, shortest distance, and fewest number of path segments to satisfy motion requirements, while avoiding sensor blind-spots. In our approach, vehicle kinematics are represented by a discretized Dubins model. To avoid collisions, each waypoint is constrained by linear inequalities representing closest distance of obstacles to a polygon specifying the vehicle's extent. To promote smooth and valid trajectories, the solved kinematic state and control variables are constrained and regularized by penalty terms in the model's cost function, which enforces physical restrictions including limits for steering angle, acceleration and speed. In this paper, we analyze trajectories obtained for several parking scenarios. Results demonstrate efficient and collision-free motion generated by the proposed technique.
This paper studies the leaderless formation flying problem with collision avoidance for a group of unmanned aerial vehicles (UAVs), which requires the UAVs to navigate through cluttered environments without colliding while maintaining the formation. The communication network among the UAVs is structured as a directed graph that includes a directed spanning tree. A novel distributed nonlinear model predictive control (NMPC) method based on the model reference adaptive consensus (MRACon) framework is proposed. Within this framework, each UAV tracks an assigned reference output generated by a linear reference model that utilizes relative measurements as input. Subsequently, the NMPC method penalizes the tracking error between the output of the reference model and that of the actual model while also establishing constraint sets for collision avoidance and physical limitations to achieve distributed and safe formation control. Finally, simulations and hardware experiments are conducted to verify the effectiveness of the proposed method.
This paper demonstrates the applicability of the safe model predictive control (SMPC) framework to autonomous driving scenarios, focusing on the design of adaptive cruise control (ACC) and automated lane-change systems. Building on the SMPC approach with priority-driven constraint softening -- which ensures the satisfaction of \emph{hard} constraints under external disturbances by selectively softening a predefined subset of adjustable constraints -- we show how the algorithm dynamically relaxes lower-priority, comfort-related constraints in response to unexpected disturbances while preserving critical safety requirements such as collision avoidance and lane-keeping. A learning-based algorithm approximating the time consuming SMPC is introduced to enable real-time execution. Simulations in real-world driving scenarios subject to unpredicted disturbances confirm that this prioritized softening mechanism consistently upholds stringent safety constraints, underscoring the effectiveness of the proposed method.
Human drivers exhibit individual preferences regarding driving style. Adapting autonomous vehicles to these preferences is essential for user trust and satisfaction. However, existing end-to-end driving approaches often rely on predefined driving styles or require continuous user feedback for adaptation, limiting their ability to support dynamic, context-dependent preferences. We propose a novel approach using multi-objective reinforcement learning (MORL) with preference-driven optimization for end-to-end autonomous driving that enables runtime adaptation to driving style preferences. Preferences are encoded as continuous weight vectors to modulate behavior along interpretable style objectives$\unicode{x2013}$including efficiency, comfort, speed, and aggressiveness$\unicode{x2013}$without requiring policy retraining. Our single-policy agent integrates vision-based perception in complex mixed-traffic scenarios and is evaluated in diverse urban environments using the CARLA simulator. Experimental results demonstrate that the agent dynamically adapts its driving behavior according to changing preferences while maintaining performance in terms of collision avoidance and route completion.
Estimating the probability of collision between spacecraft is crucial for risk management and collision-avoidance strategies. Current methods often rely on Gaussian assumptions and simplifications, which can be inaccurate in highly nonlinear scenarios. This paper presents a general and efficient approach for computing collision probabilities without relying on such assumptions. Using high-order multivariate Taylor polynomials, we propagate statistical moments of initial uncertainties to the point of closest approach between the spacecraft. To compute the probability of collision, we derive a semi-analytical expression for the probability density function (PDF) of the closest approach distance, inferred from the propagated moments using orthogonal polynomials. Tested on various short-term and long-term encounters in low-Earth orbit, our method accurately handles nonlinear dynamics, non-Gaussian uncertainties, and irregular distributions. This versatile framework advances space situational awareness by providing precise collision probability estimates in complex dynamical environments. Moreover, our methodology applies to any dynamical system with uncertainty in its initial state and is therefore not restricted to collision probability estimation.
This paper introduces a novel trajectory planner for autonomous robots, specifically designed to enhance navigation by incorporating dynamic obstacle avoidance within the Robot Operating System 2 (ROS2) and Navigation 2 (Nav2) framework. The proposed method utilizes Model Predictive Control (MPC) with a focus on handling the uncertainties associated with the movement prediction of dynamic obstacles. Unlike existing Nav2 trajectory planners which primarily deal with static obstacles or react to the current position of dynamic obstacles, this planner predicts future obstacle positions using a stochastic Vector Auto-Regressive Model (VAR). The obstacles' future positions are represented by probability distributions, and collision avoidance is achieved through constraints based on the Mahalanobis distance, ensuring the robot avoids regions where obstacles are likely to be. This approach considers the robot's kinodynamic constraints, enabling it to track a reference path while adapting to real-time changes in the environment. The paper details the implementation, including obstacle prediction, tracking, and the construction of feasible sets for MPC. Simulation results in a Gazebo environment demonstrate the effectiveness of this method in scenarios where robots must navigate around each other, showing improved collision avoidance capabilities.