arXiv subjects

Wil Thomason

Publications and source records attributed to Wil Thomason.

15 recordsLinked to original sources

arXiv2026

Think Fast and Far: Long-Horizon Online POMDP Planning via Rapid State Sampling

Partially Observable Markov Decision Processes (POMDPs) are a general and principled framework for motion planning under uncertainty. Despite tremendous improvement in the scalability of POMDP solvers, long-horizon POMDPs remain difficult to solve. To alleviate the difficulty, this paper proposes a new approximate online POMDP solver, called Reference-Based Online POMDP Planning via Rapid State Space Sampling (ROP-RAS3). ROP-RAS3 uses novel extremely fast sampling-based motion planning techniques to sample the state space and generate a diverse set of macro actions online, which are then used to bias belief-space sampling and infer high-quality policies without requiring exhaustive enumeration of the action space -- a fundamental constraint for modern online POMDP solvers. ROP-RAS3 converges to a near-optimal reference-based solution at a rate that depends on the number of sampled actions, rather than the size of the action space. ROP-RAS3 is evaluated on various long-horizon POMDPs with up to 3000 lookahead steps and 35-dimensional state spaces, where the state, action and observation spaces can be continuous, discrete, or a hybrid of discrete and continuous. Although the reference-based optimal solution may not be the same as the optimal POMDP solution, empirical results indicate that in all of these problems, in terms of success rate, ROP-RAS3 outperforms other state-of-the-art methods by up to multiple folds. We also demonstrate the capability of our approach on a physical robot demonstration. This work extends the theory and empirical results of our ISRR24 paper. Code can be found at \texttt{https://github.com/RDLLab/ROPRAS3}.

cs.RO↗

arXiv2026

Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition

Learning from Demonstration (LfD) enables robots to learn complex behaviors from expert examples, yet existing approaches often fail to generalize to new compositions of known skills without retraining. Modern generative policies model distributions over action trajectories alone, thus are unable to reason about the symbolic outcomes required for robust composition. We propose that skills should jointly model action trajectories and the symbolic outcomes they induce. To address this gap, we introduce Predicate Action Skills (PACTS), a class of closed-loop visuomotor policies that model skills as a joint generative process over action and predicate belief trajectories, producing coherent action-outcome rollouts within a single model. Jointly generating actions and predicates enables PACTS to learn internal representations that improve both action generation and predicate classification. Furthermore, we demonstrate zero-shot composition of learned skills via planning by leveraging online predicate predictions from PACTS as a symbolic interface for sequencing and monitoring execution. Project website: https://planpacts.github.io/

cs.RO↗

arXiv2026

Ultrafast Sampling-based Kinodynamic Planning via Differential Flatness

Motion planning under dynamics constraints, i.e, kinodynamic planning, enables safe robot operation by generating dynamically feasible trajectories that the robot can accurately track. For high-DOF robots such as manipulators, sampling-based motion planners are commonly used, especially for complex tasks in cluttered environments. However, enforcing constraints on robot dynamics in such planners requires solving either challenging two-point boundary value problems (BVPs) or propagating robot dynamics, both of which cause computational bottlenecks that drastically increase planning times. Meanwhile, recent efforts have shown that sampling-based motion planners can generate plans in microseconds using parallelization, but are limited to geometric paths. This paper develops FLASK, a fast parallelized sampling-based kinodynamic motion planning framework for a broad class of differentially flat robot systems, including manipulators, ground and aerial vehicles, and more. Differential flatness allows us to transform the motion planning problem from the original state space to a flat output space, where an analytical time-parameterized solution of the BVP problem can be obtained. A trajectory in the flat output space is then converted back to a closed-form dynamically feasible trajectory in the original state space, enabling fast validation via ``single instruction, multiple data" parallelism. Our framework is fast, exact, and compatible with any sampling-based motion planner, while offering theoretical guarantees on probabilistic exhaustibility and asymptotic optimality based on the closed-form BVP solutions. We extensively verify the effectiveness of our approach in both simulated benchmarks and real experiments with cluttered and dynamic environments, requiring mere microseconds to milliseconds of planning time.

cs.RO↗

arXiv2026

You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector

What happens when a pretrained generative robot policy is provided a constant initial noise as input, rather than repeatedly sampling it from a Gaussian? We demonstrate that the performance of a pretrained, frozen diffusion or flow matching policy can be improved with respect to a downstream reward by swapping the sampling of initial noise from the prior distribution (typically isotropic Gaussian) with a well-chosen, constant initial noise input - a golden ticket. We propose simple search methods to find golden tickets using Monte-Carlo policy evaluation that keeps the pretrained policy frozen, does not train any new networks, and is applicable to all diffusion/flow matching policies (and therefore many VLAs). Our approach to policy improvement makes no assumptions beyond being able to inject initial noise into the policy and calculate (sparse) task rewards of episode rollouts, making it deployable with no additional infrastructure or models. Our method improves the performance of policies in 46 out of 51 tasks across simulated and real-world robot manipulation benchmarks, with absolute improvements in success rate by up to 55% for some simulated tasks, and 28% within 60 search episodes for real-world tasks. Our approach naturally extends to multi-task settings, where we improve the average performance of a VLA policy across 7 tasks by 14% using a single noise vector. Further, we find that, a golden ticket optimized for one task can also boost performance in other related tasks for the same VLA policy. We release a codebase with pretrained policies and golden tickets for simulation benchmarks using VLAs, diffusion policies, and flow matching policies.

cs.RO↗

arXiv2025

Clebsch-Gordan Transformer: Fast and Global Equivariant Attention

The global attention mechanism is one of the keys to the success of transformer architecture, but it incurs quadratic computational costs in relation to the number of tokens. On the other hand, equivariant models, which leverage the underlying geometric structures of problem instance, often achieve superior accuracy in physical, biochemical, computer vision, and robotic tasks, at the cost of additional compute requirements. As a result, existing equivariant transformers only support low-order equivariant features and local context windows, limiting their expressiveness and performance. This work proposes Clebsch-Gordan Transformer, achieving efficient global attention by a novel Clebsch-Gordon Convolution on $\SO(3)$ irreducible representations. Our method enables equivariant modeling of features at all orders while achieving ${O}(N \log N)$ input token complexity. Additionally, the proposed method scales well with high-order irreducible features, by exploiting the sparsity of the Clebsch-Gordon matrix. Lastly, we also incorporate optional token permutation equivariance through either weight sharing or data augmentation. We benchmark our method on a diverse set of benchmarks including n-body simulation, QM9, ModelNet point cloud classification and a robotic grasping dataset, showing clear gains over existing equivariant transformers in GPU memory size, speed, and accuracy.

cs.LG↗

arXiv2025

AORRTC: Almost-Surely Asymptotically Optimal Planning with RRT-Connect

Finding high-quality solutions quickly is an important objective in motion planning. This is especially true for high-degree-of-freedom robots. Satisficing planners have traditionally found feasible solutions quickly but provide no guarantees on their optimality, while almost-surely asymptotically optimal (a.s.a.o.) planners have probabilistic guarantees on their convergence towards an optimal solution but are more computationally expensive. This paper uses the AO-x meta-algorithm to extend the satisficing RRT-Connect planner to optimal planning. The resulting Asymptotically Optimal RRT-Connect (AORRTC) finds initial solutions in similar times as RRT-Connect and uses any additional planning time to converge towards the optimal solution in an anytime manner. It is proven to be probabilistically complete and a.s.a.o. AORRTC was tested with the Panda (7 DoF) and Fetch (8 DoF) robotic arms on the MotionBenchMaker dataset. These experiments show that AORRTC finds initial solutions as fast as RRT-Connect and faster than the tested state-of-the-art a.s.a.o. algorithms while converging to better solutions faster. AORRTC finds solutions to difficult high-DoF planning problems in milliseconds where the other a.s.a.o. planners could not consistently find solutions in seconds. This performance was demonstrated both with and without single instruction/multiple data (SIMD) acceleration.

cs.RO↗

arXiv2024

Nearest-Neighbourless Asymptotically Optimal Motion Planning with Fully Connected Informed Trees (FCIT*)

Improving the performance of motion planning algorithms for high-degree-of-freedom robots usually requires reducing the cost or frequency of computationally expensive operations. Traditionally, and especially for asymptotically optimal sampling-based motion planners, the most expensive operations are local motion validation and querying the nearest neighbours of a configuration. Recent advances have significantly reduced the cost of motion validation by using single instruction/multiple data (SIMD) parallelism to improve solution times for satisficing motion planning problems. These advances have not yet been applied to asymptotically optimal motion planning. This paper presents Fully Connected Informed Trees (FCIT*), the first fully connected, informed, anytime almost-surely asymptotically optimal (ASAO) algorithm. FCIT* exploits the radically reduced cost of edge evaluation via SIMD parallelism to build and search fully connected graphs. This removes the need for nearest-neighbours structures, which are a dominant cost for many sampling-based motion planners, and allows it to find initial solutions faster than state-of-the-art ASAO (VAMP, OMPL) and satisficing (OMPL) algorithms on the MotionBenchMaker dataset while converging towards optimal plans in an anytime manner.

cs.RO↗

arXiv2024

Scaling Long-Horizon Online POMDP Planning via Rapid State Space Sampling

cs.RO↗

arXiv2024

Collision-Affording Point Trees: SIMD-Amenable Nearest Neighbors for Fast Collision Checking

Motion planning against sensor data is often a critical bottleneck in real-time robot control. For sampling-based motion planners, which are effective for high-dimensional systems such as manipulators, the most time-intensive component is collision checking. We present a novel spatial data structure, the collision-affording point tree (CAPT): an exact representation of point clouds that accelerates collision-checking queries between robots and point clouds by an order of magnitude, with an average query time of less than 10 nanoseconds on 3D scenes comprising thousands of points. With the CAPT, sampling-based planners can generate valid, high-quality paths in under a millisecond, with total end-to-end computation time faster than 60 FPS, on a single thread of a consumer-grade CPU. We also present a point cloud filtering algorithm, based on space-filling curves, which reduces the number of points in a point cloud while preserving structure. Our approach enables robots to plan at real-time speeds in sensed environments, opening up potential uses of planning for high-dimensional systems in dynamic, changing, and unmodeled environments.

cs.RO↗

arXiv2023

Stochastic Implicit Neural Signed Distance Functions for Safe Motion Planning under Sensing Uncertainty

Motion planning under sensing uncertainty is critical for robots in unstructured environments to guarantee safety for both the robot and any nearby humans. Most work on planning under uncertainty does not scale to high-dimensional robots such as manipulators, assumes simplified geometry of the robot or environment, or requires per-object knowledge of noise. Instead, we propose a method that directly models sensor-specific aleatoric uncertainty to find safe motions for high-dimensional systems in complex environments, without exact knowledge of environment geometry. We combine a novel implicit neural model of stochastic signed distance functions with a hierarchical optimization-based motion planner to plan low-risk motions without sacrificing path quality. Our method also explicitly bounds the risk of the path, offering trustworthiness. We empirically validate that our method produces safe motions and accurate risk bounds and is safer than baseline approaches.

cs.RO↗

arXiv2023

Motions in Microseconds via Vectorized Sampling-Based Planning

Modern sampling-based motion planning algorithms typically take between hundreds of milliseconds to dozens of seconds to find collision-free motions for high degree-of-freedom problems. This paper presents performance improvements of more than 500x over the state-of-the-art, bringing planning times into the range of microseconds and solution rates into the range of kilohertz, without specialized hardware. Our key insight is how to exploit fine-grained parallelism within sampling-based planners, providing generality-preserving algorithmic improvements to any such planner and significantly accelerating critical subroutines, such as forward kinematics and collision checking. We demonstrate our approach over a diverse set of challenging, realistic problems for complex robots ranging from 7 to 14 degrees-of-freedom. Moreover, we show that our approach does not require high-power hardware by also evaluating on a low-power single-board computer. The planning speeds demonstrated are fast enough to reside in the range of control frequencies and open up new avenues of motion planning research.

cs.RO↗

arXiv2023

Object Reconfiguration with Simulation-Derived Feasible Actions

3D object reconfiguration encompasses common robot manipulation tasks in which a set of objects must be moved through a series of physically feasible state changes into a desired final configuration. Object reconfiguration is challenging to solve in general, as it requires efficient reasoning about environment physics that determine action validity. This information is typically manually encoded in an explicit transition system. Constructing these explicit encodings is tedious and error-prone, and is often a bottleneck for planner use. In this work, we explore embedding a physics simulator within a motion planner to implicitly discover and specify the valid actions from any state, removing the need for manual specification of action semantics. Our experiments demonstrate that the resulting simulation-based planner can effectively produce physically valid rearrangement trajectories for a range of 3D object reconfiguration problems without requiring more than an environment description and start and goal arrangements.

cs.RO↗

arXiv2022

Task and Motion Informed Trees (TMIT*): Almost-Surely Asymptotically Optimal Integrated Task and Motion Planning

High-level autonomy requires discrete and continuous reasoning to decide both what actions to take and how to execute them. Integrated Task and Motion Planning (TMP) algorithms solve these hybrid problems jointly to consider constraints between the discrete symbolic actions (i.e., the task plan) and their continuous geometric realization (i.e., motion plans). This joint approach solves more difficult problems than approaches that address the task and motion subproblems independently. TMP algorithms combine and extend results from both task and motion planning. TMP has mainly focused on computational performance and completeness and less on solution optimality. Optimal TMP is difficult because the independent optima of the subproblems may not be the optimal integrated solution, which can only be found by jointly optimizing both plans. This paper presents Task and Motion Informed Trees (TMIT*), an optimal TMP algorithm that combines results from makespan-optimal task planning and almost-surely asymptotically optimal motion planning. TMIT* interleaves asymmetric forward and reverse searches to delay computationally expensive operations until necessary and perform an efficient informed search directly in the problem's hybrid state space. This allows it to solve problems quickly and then converge towards the optimal solution with additional computational time, as demonstrated on the evaluated robotic-manipulation benchmark problems.

cs.RO↗

arXiv2021

Counterexample-Guided Repair for Symbolic-Geometric Action Abstractions

Integrated Task and Motion Planning (TMP) provides a promising class of approaches for solving robot planning problems with intricate symbolic and geometric constraints. However, the practical usefulness of TMP planners is limited by their need for symbolic abstractions of robot actions, which are difficult to construct even for experts. We propose an approach to automatically construct and continuously improve a symbolic abstraction of a robot action via observations of the robot performing the action. This approach, called automatic abstraction repair, allows symbolic abstractions to be initially incorrect or incomplete and converge toward a correct model over time. Abstraction repair uses constrained polynomial zonotopes (CPZs), an efficient non-convex set representation, to model predicates over joint symbolic and geometric state, and performs an optimizing search over symbolic edit operations to predicate formulae to improve the correspondence of a symbolic abstraction to the behavior of a physical robot controller. In this work, we describe the aforementioned predicate model, introduce the symbolic-geometric abstraction repair problem, and present an anytime algorithm for automatic abstraction repair. We then demonstrate that abstraction repair can improve realistic action abstractions for common mobile manipulation actions from a handful of observations.

cs.RO↗

arXiv2021

Ensuring Progress for Multiple Mobile Robots via Space Partitioning, Motion Rules, and Adaptively Centralized Conflict Resolution

In environments where multiple robots must coordinate in a shared space, decentralized approaches allow for decoupled planning at the cost of global guarantees, while centralized approaches make the opposite trade-off. These solutions make a range of assumptions - commonly, that all the robots share the same planning strategies. In this work, we present a framework that ensures progress for all robots without assumptions on any robot's planning strategy by (1) generating a partition of the environment into "flow", "open", and "passage" regions and (2) imposing a set of rules for robot motion in these regions. These rules for robot motion prevent deadlock through an adaptively centralized protocol for resolving spatial conflicts between robots. Our proposed framework ensures progress for all robots without a grid-like discretization of the environment or strong requirements on robot communication, coordination, or cooperation. Each robot can freely choose how to plan and coordinate for itself, without being vulnerable to other robots or groups of robots blocking them from their goals, as long as they follow the rules when necessary. We describe our space partition and motion rules, prove that the motion rules suffice to guarantee progress in partitioned environments, and demonstrate several cases in simulated polygonal environments. This work strikes a balance between each robot's planning independence and a guarantee that each robot can always reach any goal in finite time.

cs.RO↗