We introduce a learning-guided motion planning framework that generates seed trajectories using a diffusion model for trajectory optimization. Given a workspace, our method approximates the configuration space (C-space) obstacles through an environment representation consisting of a sparse set of task-related key configurations, which is then used as a conditioning input to the diffusion model. The diffusion model integrates regularization terms that encourage smooth, collision-free trajectories during training, and trajectory optimization refines the generated seed trajectories to correct any colliding segments. Our experimental results demonstrate that high-quality trajectory priors, learned through our C-space-grounded diffusion model, enable the efficient generation of collision-free trajectories in narrow-passage environments, outperforming previous learning- and planning-based baselines. Videos and additional materials can be found on the project page: https://kiwi-sherbet.github.io/PRESTO.

Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent's ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement.

This paper explores general multi-robot task and motion planning, where multiple robots in close proximity manipulate objects while satisfying constraints and a given goal. In particular, we formulate the plan refinement problem—which, given a task plan, finds valid assignments of variables corresponding to solution trajectories—as a hybrid constraint satisfaction problem. The proposed algorithm follows several design principles that yield the following features: (1) efficient solution finding due to sequential heuristics and implicit time and roadmap representations, and (2) maximized feasible solution space obtained by introducing minimally necessary coordination-induced constraints and not relying on prevalent simplifications that exist in the literature. The evaluation results demonstrate the planning efficiency of the proposed algorithm, outperforming the synchronous approach in terms of makespan.

In realistic applications of object search, robots will need to locate target objects in complex environments while coping with unreliable sensors, especially for small or hard-to-detect objects. In such settings, correlational information can be valuable for planning efficiently. Previous approaches that consider correlational information typically resort to ad-hoc, greedy search strategies. We introduce the Correlational Object Search POMDP (COS-POMDP), which models correlations while preserving optimal solutions with a reduced state space. We propose a hierarchical planning algorithm to scale up COS-POMDPs for practical domains. Our evaluation, conducted with the AI2-THOR household simulator and the YOLOv5 object detector, shows that our method finds objects more successfully and efficiently compared to baselines, particularly for hard-to-detect objects such as srub brush and remote control.

We study the problem of searching for and tracking a collection of moving targets using a robot with a limited field-of-view (FOV) sensor. The actual number of targets present in the environment is not knowna priori. We propose a search and tracking framework based on the concept of Bayesian random finite sets (RFSs). Specifically, we generalize the Gaussian mixture probability hypothesis density (GM-PHD) filter which was previously applied for tracking problems to allow for simultaneous search and tracking with a limited FOV sensor. The proposed framework can extract individual target tracks as well as estimate the number and the spatial density of targets. We also show how to use the Gaussian process (GP) regression to extract and predict unknown target trajectories in this framework. We demonstrate the efficacy of our techniques through representative simulations and a real data collected from an aerial robot.Note to Practitioners—This article is motivated by search-and-rescue operations where a robot with limited field-of-view (FOV) is used to search and track lost targets. This article presents an estimation and planning framework to estimate the position of targets and track them over time. The key feature of the proposed algorithm is that it can deal with an unknown and varying number of targets. The framework can also deal with an unknown motion model for targets which itself can be complex. The algorithm is shown to be robust to a poor initialization and can handle an initial belief which overestimates or underestimates the actual number of targets. The proposed scheme includes various user-defined parameters. It is recommended to tune these parametersa prioriusing simulations for a better performance. Incorporating a multirobot approach into the proposed algorithm and finding a better planning strategy that minimizes the time are potential future works.

We present a task-and-motion planning (TAMP) algorithm robust against a human operator's cooperative or adversarial interventions. Interventions often invalidate the current plan and require replanning on the fly. Replanning can be computationally expensive and often interrupts seamless task execution. We introduce a dynamically reconfigurable planning methodology with behavior tree-based control strategies toward reactive TAMP, which takes the advantage of previous plans and incremental graph search during temporal logic-based reactive synthesis. Our algorithm also shows efficient recovery functionalities that minimize the number of replanning steps. Finally, our algorithm produces a robust, efficient, and complete TAMP solution. Our experimental results show the algorithm results in superior manipulation performance in both simulated and real-world tasks.

Our work is motivated by environmental monitoring tasks, where finding the global maxima (i.e., hotspot) of a spatially varying field is crucial. We investigate the problem of identifying the hotspot for fields that can be sensed using an Unmanned Aerial Vehicle (UAV) equipped with a downward-facing camera. The UAV has a limited time budget which it can use for learning the unknown field and identifying the hotspot. Our contribution is to show how this problem can be formulated as a novel multi-fidelity variant of the Gaussian Process (GP) multi-armed bandit problem. The novelty is two-fold: (i) unlike standard multi-armed bandit settings, the rewards of the arms are correlated with each other; and (ii) unlike standard GP regression, the measurements in our problem are images (i.e., vector measurements) whose quality depends on the altitude of the UAV. We present a strategy for finding the sequence of UAV sensing locations and empirically compare it with several baselines. Experimental results using images gathered onboard a UAV are also presented and the scalability of the proposed methodology is assessed in a large-scale simulated environment.

Anytime motion planners are widely used in robotics. However, the relationship between their solution quality and computation time is not well understood, and thus, determining when to quit planning and start execution is unclear. In this paper, we address the problem of deciding when to stop deliberation under bounded computational capacity, so called meta-reasoning, for anytime motion planning. We propose data-driven learning methods, model-based and model-free meta-reasoning, that are applicable to different environment distributions and agnostic to the choice of anytime motion planners. As a part of the framework, we design a convolutional neural network-based optimal solution predictor that predicts the optimal path length from a given 2D workspace image. We empirically evaluate the performance of the proposed methods in simulation in comparison with baselines.

Robots operating in households must find objects on shelves, under tables, and in cupboards. In such environments, it is crucial to search efficiently at 3D scale while coping with limited field of view and the complexity of searching for multiple objects. Principled approaches to object search frequently use Partially Observable Markov Decision Process (POMDP) as the underlying framework for computing search strategies, but constrain the search space in 2D. In this paper, we present a POMDP formulation for multi-object search in a 3D region with a frustum-shaped field-of-view. To efficiently solve this POMDP, we propose a multi-resolution planning algorithm based on online Monte-Carlo tree search. In this approach, we design a novel octree-based belief representation to capture uncertainty of the target objects at different resolution levels, then derive abstract POMDPs at lower resolutions with dramatically smaller state and observation spaces. Evaluation in a simulated 3D domain shows that our approach finds objects more efficiently and successfully compared to a set of baselines without resolution hierarchy in larger instances under the same computational requirement. We demonstrate our approach on a mobile robot to find objects placed at different heights in two 10m2×2m regions by moving its base and actuating its torso.

In this paper, we study the problem of exploring a translating plume with a team of aerial robots. The shape and the size of the plume are unknown to the robots. The objective is to find a tour for each robot such that they collectively explore the plume. Specifically, the tours must be such that each point in the plume must be visible from the field-of-view of some robot along its tour. We propose a recursive Depth-First Search (DFS)-based algorithm that yields a constant competitive ratio for the exploration problem. The competitive ratio is 2(Sr+ Sp)(R+⌊log R⌋)/(Sr+ Sp)(R+⌊log R⌋) where R is the number of robots, and Sr and Sp are the robot speed and the plume speed, respectively. We also consider a more realistic scenario where the plume shape is not restricted to grid cells but an arbitrary shape. We show our algorithm has 2(Sr+ Sp)(18 R+⌊log R⌋)/(Sr+ Sp)(1+⌊log R⌋) competitive ratio under the fat condition. We empirically verify our algorithm using simulations.

We introduce and study the problem of planning a trajectory for an agent to carry out a reconnaissance mission while avoiding being detected by an adversarial guard. This introduces a multi-objective version of classical visibility-based target search and pursuit-evasion problem. In our formulation, the agent receives a positive reward for increasing its visibility (by exploring new regions) and a negative penalty every time it is detected by the guard. The objective is to find a finite-horizon path for the agent that balances the trade off between maximizing visibility and minimizing detectability.We model this problem as a discrete, sequential, two-player, zero-sum game. We use two types of game tree search algorithms to solve this problem: minimax search tree and Monte-Carlo search tree. Both search trees can yield the optimal policy but may require possibly exponential computational time and space. We propose several pruning techniques to reduce the computational cost while still preserving optimality guarantees. Simulation results show that the proposed strategy prunes approximately three orders of magnitude nodes as compared to the brute-force strategy. We also find that the Monte-Carlo search tree saves approximately one order of computational time as compared to the minimax search tree.

We study two multi-robot assignment problems for multi-target tracking. We consider distributed approaches in order to deal with limited sensing and communication ranges. We seek to simultaneously assign trajectories and targets to the robots. Our focus is on local algorithms that achieve performance close to the optimal algorithms with limited communication. We show how to use a local algorithm that guarantees a bounded approximate solution within O(hlog1/ε) communication rounds. We compare with a greedy approach that achieves a 2-approximation in as many rounds as the number of robots. Simulation results show that the local algorithm is an effective solution to the assignment problem.

This paper presents a fire heading estimation for solving the autonomous navigation problem of a firefighting robot in smoke-filled indoor fire environment. In smoke-filled fire environments, firefighters and firefighting robots experience difficulty maintaining direction while finding the fire source. To solve this, the statistical texture features in thermal images were analyzed and fused by using Bayesian estimation to compute the vertical and horizontal fire heading. For its validation, a large-scaled test-bed was built with a hallway and two rooms, with one of the rooms having a real size fire generating dense and dark smoke. The proposed method probabilistically computed the fire-heading toward the entrance of the hallway then guided the robot to the room with the actual fire, all while navigating in a smoke-filled situation. The experimental results have demonstrated the effectiveness of this method in indoor fire environments.

We study the problem of searching and tracking a collection of moving targets using a robot with a limited Field-of-View (FoV) sensor. The actual number of targets present in the environment is not known a priori. We propose a search and tracking framework based on the concept of Bayesian Random Finite Sets (RFSs). Specifically, we generalize the Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter which was previously applied for only tracking problems to allow for simultaneous search and tracking. The proposed framework can extract individual target tracks as well as estimate the number and spatial density of the targets. We also show how to use Gaussian Process (GP) regression to extract and predict nonlinear target trajectories in this framework. We demonstrate the efficacy of our techniques through representative simulations where we also compare the performance of two active control strategies.

Human-following in a cluttered environment is one of the challenging issues for mobile service robot applications. Since a laser range finder (LRF) is commonly installed for autonomous navigation, it is advantageous to adopt an LRF for detection and tracking humans. In this paper, we aim at the reliable human tracking performances in a dynamic cluttered environment. The key idea is to develop a hierarchical sample-based joint probabilistic data association filter (HSJPDAF) by focusing on the leg positions as well as human positions. The proposed HSJPDAF consists of two levels in order to consider the interdependence between targets. Possible locations of multiple human targets can be simultaneously estimated on the basis of Bayesian filtering. Comparison with the general technique was carried out to verify the performance of HSJPDAF in both artificial indoor and real-world environments. Owing to the hierarchical framework, the proposed method shows the improved robustness by reducing the target loss rate significantly in a dynamic cluttered environment.

Human tracking has become an important part in the mobile robotics community to achieve human-friendly navigation. When it comes to extracting humans from sensor data when there are many people in its environment, matching between targets and measurements can be a significant problem. In this paper, a single laser range finder is adopted as a sensor, and we implement JPDAFs, one of the most eminent methods for matching, to track humans. The performance is tested through experiments on actual human walking.