Papers

@inproceedings{Bekris:2024aa,
title = {The State of Robot Motion Generation},
author = {K Bekris and J Doerr and P Meng and S Tangirala},
url = {https://arxiv.org/abs/2410.12172 https://pracsys.cs.rutgers.edu/papers/the-state-of-robot-motion-generation/},
year = {2024},
date = {2024-12-01},
booktitle = {International Symposium of Robotics Research (ISRR)},
address = {Long Beach, California},
abstract = {This paper first reviews the large spectrum of methods for generating robot motion proposed over the 50 years of robotics research culminating to recent developments. It crosses the boundaries of methodologies, which are typically not surveyed together, from those that operate over explicit models to those that learn implicit ones. The paper concludes with a discussion of the current state-of-the-art and the properties of the varying methodologies highlighting opportunities for integration.},
keywords = {Dynamics, Learning, Planning},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{Lu:2023ab,
title = {Self-Supervised Learning of Object Segmentation from Unlabeled RGB-D Videos},
author = {S Lu and Y Deng and A Boularias and K Bekris},
url = {https://arxiv.org/abs/2304.04325},
year = {2023},
date = {2023-05-01},
booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
address = {London, UK},
abstract = {This work proposes a self-supervised learning system for segmenting rigid objects in RGB images. The proposed pipeline is trained on unlabeled RGB-D videos of static objects, which can be captured with a camera carried by a mobile robot. A key feature of the self-supervised training process is a graph-matching algorithm that operates on the over-segmentation output of the point cloud that is reconstructed from each video. The graph matching, along with point cloud registration, is able to find reoccurring object patterns across videos and combine them into 3D object pseudo labels, even under occlusions or different viewing angles. Projected 2D object masks from 3D pseudo labels are used to train a pixel-wise feature extractor through contrastive learning. During online inference, a clustering method uses the learned features to cluster foreground pixels into object segments. Experiments highlight the method's effectiveness on both real and synthetic video datasets, which include cluttered scenes of tabletop objects. The proposed method outperforms existing unsupervised methods for object segmentation by a large margin.},
keywords = {Learning, Perception},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{McMahon:2022ab,
title = {Terrain-Aware Learned Controllers for Sampling-Based Kinodynamic Planning Over Physically Simulated Terrains},
author = {T McMahon and A Sivaramakrishnan and K Kedia and E Granados and K Bekris},
url = {https://ieeexplore.ieee.org/document/9982136},
year = {2022},
date = {2022-06-01},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
abstract = {This paper explores learning an effective controller for improving the efficiency of kinodynamic planning for vehicular systems navigating uneven terrains. It describes the pipeline for training the corresponding controller and using it for motion planning purposes. The training process uses a soft actor-critic approach with hindsight experience replay to train a model, which is parameterized by the incline of the robot's local terrain. This trained model is then used during the expansion process of an asymptotically optimal kinodynamic planner to generate controls that allow the robot to reach desired local states. It is also used to define a heuristic cost-to-go function for the planner via a wavefront operation that estimates the cost of reaching the global goal. The cost-to-go function is used both for selecting nodes for expansion as well as for generating local goals for the controller to expand towards. The accompanying experimental section applies the integrated planning solution on models of all-terrain robots in a variety of physically simulated terrains. It shows that the proposed terrain-aware controller and the proposed wavefront function based on the cost-to-go model enable motion planners to find solutions in less time and with lower cost than alternatives. An ablation study emphasizes the benefits of a learned controller that is parameterized by the incline of the robot's local terrain as well as of an incremental training process for the controller.},
keywords = {Dynamics, Learning, Planning},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{Wen:2022ab,
title = {You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration},
author = {B Wen and W Lian and K Bekris and S Schaal},
url = {https://www.roboticsproceedings.org/rss18/p044.pdf},
year = {2022},
date = {2022-06-01},
booktitle = {Robotics: Science and Systems (RSS)},
abstract = {Promising results have been achieved recently in category-level manipulation that generalizes across object instances. Nevertheless, it often requires expensive real-world data collection and manual specification of semantic keypoints for each object category and task. Additionally, coarse keypoint predictions and ignoring intermediate action sequences hinder adoption in complex manipulation tasks beyond pick-and-place. This work proposes a novel, category-level manipulation framework that leverages an object-centric, category-level representation and model-free 6 DoF motion tracking. The canonical object representation is learned solely in simulation and then used to parse a category-level, task trajectory from a single demonstration video. The demonstration is reprojected to a target trajectory tailored to a novel object via the canonical representation. During execution, the manipulation horizon is decomposed into long range, collision-free motion and last-inch manipulation. For the latter part, a category-level behavior cloning (CatBC) method leverages motion tracking to perform closed-loop control. CatBC follows the target trajectory, projected from the demonstration and anchored to a dynamically selected category-level coordinate frame. The frame is automatically selected along the manipulation horizon by a local attention mechanism. This framework allows to teach different manipulation strategies by solely providing a single demonstration, without complicated manual programming. Extensive experiments demonstrate its efficacy in a range of challenging industrial tasks in high precision assembly, which involve learning complex, long-horizon policies. The process exhibits robustness against uncertainty due to dynamics as well as generalization across object instances and scene configurations.},
note = {Nomination for Best Paper Award},
keywords = {Learning, Manipulation, Perception},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{Wang:2021ab,
title = {Sim2Sim Evaluation of a Novel Data-Efficient Differentiable Physics Engine for Tensegrity Robots},
author = {K Wang and M Aanjaneya and K Bekris},
url = {https://arxiv.org/abs/2011.04929},
year = {2021},
date = {2021-09-01},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
abstract = {Learning policies in simulation is promising for reducing human effort when training robot controllers. This is especially true for soft robots that are more adaptive and safe but also more difficult to accurately model and control. The sim2real gap is the main barrier to successfully transfer policies from simulation to a real robot. System identification can be applied to reduce this gap but traditional identification methods require a lot of manual tuning. Data-driven alternatives can tune dynamical models directly from data but are often data hungry, which also incorporates human effort in collecting data. This work proposes a data-driven, end-to-end differentiable simulator focused on the exciting but challenging domain of tensegrity robots. To the best of the authors' knowledge, this is the first differentiable physics engine for tensegrity robots that supports cable, contact, and actuation modeling. The aim is to develop a reasonably simplified, data-driven simulation, which can learn approximate dynamics with limited ground truth data. The dynamics must be accurate enough to generate policies that can be transferred back to the ground-truth system. As a first step in this direction, the current work demonstrates sim2sim transfer, where the unknown physical model of MuJoCo acts as a ground truth system. Two different tensegrity robots are used for evaluation and learning of locomotion policies, a 6-bar and a 3-bar tensegrity. The results indicate that only 0.25% of ground truth data are needed to train a policy that works on the ground truth system when the differentiable engine is used for training against training the policy directly on the ground truth system.},
keywords = {Dynamics, Learning, Soft-Robots},
pubstate = {published},
tppubtype = {inproceedings}
}