Author name cluster

Kyle Vedder

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

ICLR Conference 2025 Conference Paper

Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model

Long Le
Jason Xie
William Liang
Hung-Ju Wang
Yue Yang
Yecheng Jason Ma 0001
Kyle Vedder
Arjun Krishna

Interactive 3D simulated objects are crucial in AR/VR, animations, and robotics, driving immersive experiences and advanced automation. However, creating these articulated objects requires extensive human effort and expertise, limiting their broader applications. To overcome this challenge, we present Articulate-Anything, a system that automates the articulation of diverse, complex objects from many input modalities, including text, images, and videos. Articulate-Anything leverages vision-language models (VLMs) to generate code that can be compiled into an interactable digital twin for use in standard 3D simulators. Our system exploits existing 3D asset datasets via a mesh retrieval mechanism, along with an actor-critic system that iteratively proposes, evaluates, and refines solutions for articulating the objects, self-correcting errors to achieve a robust out- come. Qualitative evaluations demonstrate Articulate-Anything's capability to articulate complex and even ambiguous object affordances by leveraging rich grounded inputs. In extensive quantitative experiments on the standard PartNet-Mobility dataset, Articulate-Anything substantially outperforms prior work, increasing the success rate from 8.7-11.6\% to 75\% and setting a new bar for state-of-art performance. We further showcase the utility of our generated assets by using them to train robotic policies for fine-grained manipulation tasks that go beyond basic pick and place.

Details

ICLR Conference 2025 Conference Paper

Neural Eulerian Scene Flow Fields

Kyle Vedder
Neehar Peri
Ishan Khatri
Siyi Li
Eric Eaton
Mehmet Kemal Kocamaz
Yue Wang
Zhiding Yu

We reframe scene flow as the task of estimating a continuous space-time ordinary differential equation (ODE) that describes motion for an entire observation sequence, represented with a neural prior. Our method, EulerFlow, optimizes this neural prior estimate against several multi-observation reconstruction objectives, enabling high quality scene flow estimation via self-supervision on real-world data. EulerFlow works out-of-the-box without tuning across multiple domains, including large-scale autonomous driving scenes and dynamic tabletop settings. Remarkably, EulerFlow produces high quality flow estimates on small, fast moving objects like birds and tennis balls, and exhibits emergent 3D point tracking behavior by solving its estimated ODE over long-time horizons. On the Argoverse 2 2024 Scene Flow Challenge, EulerFlow outperforms all prior art, surpassing the next-best unsupervised method by more than 2.5 times, and even exceeding the next-best supervised method by over 10%. See https://vedder.io/eulerflow for interactive visuals.

Details

ICLR Conference 2024 Conference Paper

ZeroFlow: Scalable Scene Flow via Distillation

Kyle Vedder
Neehar Peri
Nathaniel Chodosh
Ishan Khatri
Eric Eaton
Dinesh Jayaraman
Yang Liu
Deva Ramanan

Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimization techniques, but require on the order of tens of seconds to process full-size point clouds, making them unusable as computer vision primitives for real-time applications such as open world object detection. Feedforward methods are considerably faster, running on the order of tens to hundreds of milliseconds for full-size point clouds, but require expensive human supervision. To address both limitations, we propose _Scene Flow via Distillation_, a simple, scalable distillation framework that uses a label-free optimization method to produce pseudo-labels to supervise a feedforward model. Our instantiation of this framework, _ZeroFlow_, achieves **state-of-the-art** performance on the _Argoverse 2 Self-Supervised Scene Flow Challenge_ while using zero human labels by simply training on large-scale, diverse unlabeled data. At test-time, ZeroFlow is over 1000$\times$ faster than label-free state-of-the-art optimization-based methods on full-size point clouds (34 FPS vs 0.028 FPS) and over 1000$\times$ cheaper to train on unlabeled data compared to the cost of human annotation (\\$394 vs ~\\$750,000). To facilitate further research, we will release our code, trained model weights, and high quality pseudo-labels for the Argoverse 2 and Waymo Open datasets.

Details

IROS Conference 2022 Conference Paper

Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems

Kyle Vedder
Eric Eaton

Bird's Eye View (BEV) is a popular representation for processing 3D point clouds, and by its nature is fundamentally sparse. Motivated by the computational limitations of mobile robot platforms, we create a fast, high-performance BEV 3D object detector that maintains and exploits this input sparsity to decrease runtimes over non-sparse baselines and avoids the tradeoff between pseudoimage area and runtime. We present results on KITTI, a canonical 3D detection dataset, and Matterport-Chair, a novel Matterport3D-derived chair detection dataset from scenes in real furnished homes. We evaluate runtime characteristics using a desktop GPU, an embedded ML accelerator, and a robot CPU, demonstrating that our method results in significant detection speedups (2 × or more) for embedded systems with only a modest decrease in detection quality. Our work represents a new approach for practitioners to optimize models for embedded systems by maintaining and exploiting input sparsity throughout their entire pipeline to reduce runtime and resource usage while preserving detection performance. All models, weights, experimental configurations, and datasets used are publicly available 1 1 https://vedder.io/sparse_point_pillars.

Details

AIJ Journal 2021 Journal Article

X*: Anytime Multi-Agent Path Finding for Sparse Domains using Window-Based Iterative Repairs

Kyle Vedder
Joydeep Biswas

Real-world multi-agent systems such as warehouse robots operate under significant time constraints – in such settings, rather than spending significant amounts of time solving for optimal paths, it is instead preferable to find valid, collision-free paths quickly, even if suboptimal, and given additional time, to iteratively refine such paths to improve their cost. In such domains, we observe that agent-agent collisions are sparse – they involve small local subsets of agents, and are geographically contained within a small region of the overall space. Leveraging this insight, we can first plan paths for each agent individually, and in the cases of collisions between agents, perform small local repairs limited to local subspace windows. As time permits, these windows can be successively grown and the repairs within them refined, thereby improving the path quality, and eventually converging to the global joint optimal solution. Using these insights, we present two algorithmic contributions: 1) the Windowed Anytime Multiagent Planning Framework (WAMPF) for a class of anytime planners that quickly generate valid paths with suboptimality estimates and generate optimal paths given sufficient time, and 2) X*, an efficient WAMPF-based planner. X* is able to efficiently find successive valid solutions by employing re-use techniques during the repair growth step of WAMPF. Experimentally, we demonstrate that in sparse domains: 1) X* outperforms state-of-the-art anytime or optimal MAPF solvers in time to valid path, 2) X* is competitive with state-of-the-art anytime or optimal MAPF solvers in time to optimal path, 3) X* quickly converges to very tight suboptimality bounds, and 4) X* is competitive with state-of-the-art suboptimal MAPF solvers in time to valid path for small numbers of agents while providing much higher quality paths.

Details DOI

AAMAS Conference 2019 Conference Paper

X*: Anytime Multiagent Planning With Bounded Search

Kyle Vedder
Joydeep Biswas

Multi-agent planning in dynamic domains is a challenging problem: the size of the configuration space increases exponentially in the number of agents, and plans need to be re-evaluated periodically to account for moving obstacles. However, we have two key insights that hold in several domains: 1) conflicts between multi-agent plans often have geometrically local resolutions within a small repair window, even if such local resolutions are not globally optimal; and 2) the partial search tree for such local resolutions can then be iteratively improved over successively larger windows to eventually compute the global optimal plan. Building upon these two insights, we introduce 1) a class of anytime multiagent planning solvers, 2) a naïve solver in this class, and 3) an efficient solver in this class which reuses prior search information when improving a solution.

PDF