Sequence models have demonstrated remarkable success in behavioral planning by leveraging previously collected demonstrations. However, solving multi-task missions remains a significant challenge, particularly when the planner must adapt to unseen constraints and tasks, such as discovering goals and unlocking doors. Such behavioral planning problems are challenging to solve due to: a) agents failing to adapt beyond the single task learned through their reward function, and b) inability to generalize to new environments, e.g., those with walls and locked doors, when trained only in planar environments. Consequently, state-of-the-art decision-making methods are limited to missions where the required tasks are well-represented in the training demonstrations and can be solved within a short (temporal) planning horizon. To address this, we propose GenPlan: a stochastic and adaptive planner that leverages discrete-flow models for generative sequence modeling, enabling sample-efficient exploration and exploitation. This framework relies on an iterative denoising procedure to generate a sequence of goals and actions. This approach captures multi-modal action distributions and facilitates goal and task discovery, thereby generalizing to out-of-distribution tasks and environments, i.e., missions not part of the training data. We demonstrate the effectiveness of our method through multiple simulation environments. Notably, GenPlan outperforms state-of-the-art methods by over 10% on adaptive planning tasks, where the agent adapts to multi-task missions while leveraging demonstrations from single-goal-reaching tasks.

Functional integration is a growing trend in vehicle control, often involving the coordination of multiple controllers to achieve various objectives simultaneously. The need for flexibility and reliability has led to a “plug-and-play” approach in control system design, which presents challenges for traditional integrated model predictive control (MPC). Agent-based model predictive control (AMPC) has recently emerged as a distributed solution that treats controllers as agents, creating a collaborative framework among them to reach a common goal. However, this approach struggles to manage distributed conflicting objectives when agents are coupled or interdependent. To address this, we propose a novel, practical distributed control scheme called multi-objective AMPC, which adapts the alternating direction method of multipliers (ADMM) into a general control strategy that approximates global optimization while decoupling objectives. We systematically develop three formulations that maintain convergence while addressing control regularization and inequality constraints, applying them to complex vehicle control systems for the first time. The proposed method has been tested on two vehicle control scenarios with a multi-objective topology. Different formulations are compared through simulations, and the most computationally efficient one was implemented on an electric vehicle for real-world evaluations. The results demonstrate that the proposed multi-objective AMPC can converge approximately to the same global optimum as integrated MPC with greater flexibility and the potential to reduce computational costs.

As autonomous vehicles (AVs) become more common on public roads, their interaction with human-driven vehicles (HVs) in mixed traffic is inevitable. This requires new control strategies for AVs to handle the unpredictable nature of HVs. This study focused on safe control in mixed-vehicle platoons consisting of both AVs and HVs, particularly during longitudinal car-following scenarios. We introduce a novel model that combines a conventional first-principles model with a Gaussian process (GP) machine learning-based model to better predict HV behavior. Our results showed a significant improvement in predicting HV speed, with a 35.64% reduction in the root mean square error compared with the use of the first-principles model alone. We developed a new control strategy called GP-MPC, which uses the proposed HV model for safer distance management between vehicles in the mixed platoon. The GP-MPC strategy effectively utilizes the capacity of the GP model to assess uncertainties, thereby significantly enhancing safety in challenging traffic scenarios, such as emergency braking scenarios. In simulations, the GP-MPC strategy outperformed the baseline MPC method, offering better safety and more efficient vehicle movement in mixed traffic.

With the increasing presence of autonomous vehicles (AVs) on public roads, developing robust control strategies to navigate the uncertainty of human-driven vehicles (HVs) is crucial. This paper introduces an advanced method for modeling HV behavior, combining a first-principles model with Gaussian process (GP) learning to enhance velocity prediction accuracy and provide a measurable uncertainty. We validated this innovative HV model using real-world data from field experiments and applied it to develop a GP-enhanced model predictive control (GP-MPC) strategy. This strategy aims to improve safety in mixed vehicle platoons by integrating uncertainty assessment into distance constraints. Comparative simulation studies with a conventional model predictive control (MPC) approach demonstrated that our GP-MPC strategy ensures more reliable safe distancing and fosters efficient vehicular dynamics, achieving notably higher speeds within the platoon. By incorporating a sparse GP technique in HV modeling and adopting a dynamic GP prediction within the MPC framework, we significantly reduced the computation time of GP-MPC, marking it only 4.6% higher than that of the conventional MPC. This represents a substantial improvement, making the process about 100 times faster than our preliminary work without these approximations. Our findings underscore the effectiveness of learning-based HV modeling in enhancing both safety and operational efficiency in mixed-traffic environments, paving the way for more harmonious AV-HV interactions.

Agent-based model predictive control (AMPC) has recently been proposed as a distributed scheme that collaborates with all agents to achieve optimal holistic performance. However, its optimality highly depends on the prediction accuracy that requires all agents or their contributions to be known, which is too idealistic for actual implementation. This research proposes a novel practical hybrid control scheme - learning agent-based MPC (LAMPC), combining the model-based AMPC approach and data-based learning methods to improve the holistic vehicle performance for multi-agent systems. The Gaussian process regression (GPR) enhanced by an online data management strategy serves as the learning core to predict unknown contributions. A novel multi-step prediction mechanism leverages the GPR learning potential along the horizon. The predicted mean, representing the learned unknown contributions, completes the system model in the MPC for more accurate control. Meanwhile, a stochastic framework is formulated to guarantee control safety and feasibility using soft chance constraints based on the prediction variance. Both simulations and experiments show that, with the learning capability, LAMPC outperforms the traditional AMPC. LAMPC can achieve higher tracking performance in well-learned scenarios and always guarantee constraint satisfaction even in less-learned scenarios. Moreover, the proposed hybrid control scheme is efficient for real-time implementation and is flexible to any control agent topology.

Urban Air Mobility, the scenario where hundreds of manned and Unmanned Aircraft Systems (UASs) carry out a wide variety of missions (e.g., moving humans and goods within the city), is gaining acceptance as a transportation solution of the future. One of the key requirements for this to happen is safely managing the air traffic in these urban airspaces. Due to the expected density of the airspace, this requires fast autonomous solutions that can be deployed online. We propose Learning-‘N-Flying (LNF), a multi-UAS Collision Avoidance (CA) framework. It is decentralized, works on the fly, and allows autonomous Unmanned Aircraft System (UAS)s managed by different operators to safely carry out complex missions, represented using Signal Temporal Logic, in a shared airspace. We initially formulate the problem of predictive collision avoidance for two UASs as a mixed-integer linear program, and show that it is intractable to solve online. Instead, we first develop Learning-to-Fly (L2F) by combining (1) learning-based decision-making and (2) decentralized convex optimization-based control. LNF extends L2F to cases where there are more than two UASs on a collision path. Through extensive simulations, we show that our method can run online (computation time in the order of milliseconds) and under certain assumptions has failure rates of less than 1% in the worst case, improving to near 0% in more relaxed operations. We show the applicability of our scheme to a wide variety of settings through multiple case studies.

In multi-agent systems, robots transmit their planned trajectories to each other or to a central controller, and each receiver plans its own actions by maximizing a measure of mission satisfaction. For missions expressed in temporal logic, the robustness function plays the role of satisfaction measure. Currently, a Piece-Wise Linear (PWL) or piece-wise constant reconstruction is used at the receiver. This allows an efficient robustness computation algorithm - a.k.a. monitoring - but is not adaptive to the signal class of interest, and does not leverage the compression properties of more general representations. When communication capacity is at a premium, this is a serious bottleneck. In this paper we first show that the robustness computation is significantly affected by how the continuous-time signal is reconstructed from the received samples, which can mean the difference between a successful control and a crash. We show that monitoring general spline-based reconstructions yields a smaller robustness error, and that it can be done with the same time complexity as monitoring the simpler PWL reconstructions. Thus robustness computation can now be adapted to the signal class of interest. We further show that the monitoring error is tightly upper-bounded by the L∞ signal reconstruction error. We present a (non-linear) L∞-based scheme which yields even lower monitoring error than the spline-based schemes (which have the advantage of being faster to compute), and illustrate all results on two case studies. As an application of these results, we show how time-frequency specifications can be efficiently monitored online.

Autonomous vehicles promise significant benefits to society, from reduced accident rates to greater mobility for the elderly. The biggest challenge in the design of autonomous vehicles comes from the uncertainty of the environment in which they will operate. Their control algorithms must be able to cope with driving events that occur on widely ranging time scales. For example, relaxed rural driving can accommodate planning actions every few seconds, while imminent collision avoidance requires planning and actuation on the order of a few milliseconds. Thus 'real-time' performance will imply different things depending on the context.

Control software of autonomous robots has stringent real-time requirements that must be met to achieve the control objectives. One source of variability in the performance of a control system is the execution time and accuracy of the state estimator that provides the controller with state information. This estimator is typically perception-based (e.g., Computer Vision-based) and is computationally expensive. When the computational resources of the hardware platform become overloaded, the estimation delay can compromise control performance and even stability. In this paper, we define a framework for co-designing anytime estimation and control algorithms, in a manner that accounts for implementation issues like delays and inaccuracies. We construct an anytime perception-based estimator from standard off-the-shelf Computer Vision algorithms, and show how to obtain a trade-off curve for its delay vs estimate error behaviour. We use this anytime estimator in a controller that can use this trade-off curve at runtime to achieve its control objectives at a reduced energy cost. When the estimation delay is too large for correct operation, we provide an optimal manner in which the controller can use this curve to reduce estimation delay at the cost of higher inaccuracy, all the while guaranteeing basic objectives are met. We illustrate our approach on an autonomous hexrotor and demonstrate its advantage over a system that does not exploit co-design.