Object Rearrangement Using Learned Implicit Collision Functions

Danielczuk, Michael; Mousavian, Arsalan; Eppner, Clemens; Fox, Dieter

doi:10.1109/icra48506.2021.9561516

Cited by 45 publications

(50 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, setting up a real-world TAMP system often requires substantial task-specific knowledge and accurate 3D models of the environment, significantly limiting the environments to which the system can generalize. To address this challenge, recent work has adopted deep learning-based approaches for robotic manipulation, for instance, on grasp planning [44,47,48,62,65], motion planning [7,57], and reasoning about spatial relations [20,36,49].…”

Section: Related Workmentioning

confidence: 99%

“…The planner classifies each relative transform as feasible if the object at the predicted transform is not colliding with any other objects in the scene. We used pre-trained SceneCollisionNet [7] to check the collision of the object at the predicted transformation. The feasible objects are then ranked based on score S = |r| + λ|t|, where r is the relative rotation transformation in radians, t is the relative translation in cm and λ = 0.2 in our experiments.…”

Section: Planning and Executionmentioning

confidence: 99%

“…A recent approach called NeRP, proposed by Qureshi et al [51], has allowed for rearranging objects unseen at the training time, by representing the observed objects with learned embeddings. It also removes the need of explicit object pose estimation for planning by leveraging recent progress on learning-based grasp planners [62] and collision detectors [7]. However, NeRP only allows moving objects with 2D in-plane translations on the table surface and allows no change in their orientation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

IFOR: Iterative Flow Minimization for Robotic Object Rearrangement

Goyal¹,

Mousavian²,

Paxton³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Figure 1. An example of IFOR being applied to real data. The initial and goal scenes are shown on the left.Our approach allows the robot to repeatedly identify transformations that will minimize the flow for various objects between the current and goal scenes. It can then repeatedly grasp, move, and place objects, rotating as necessary, in order to achieve the configuration in the goal scene. The system is trained completely on synthetic data and transfers to the real world in zero-shot manner.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Planning and Executionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

IFOR: Iterative Flow Minimization for Robotic Object Rearrangement

Goyal¹,

Mousavian²,

Paxton³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…If the number of predicted grasps for an object is too low, we reduce the confidence threshold to 0.19. In the end we execute the most confident grasp that is kinematically reachable and where the robot does not collide with the scene [38].…”

Section: A Inferencementioning

confidence: 99%

“…In our experiments, we use the Intel Realsense L515 LiDAR camera mounted on a tripod for both RGB and depth data. Robot motions are generated using [38].…”

Section: Real Robot Grasp Experimentsmentioning

confidence: 99%

Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes

Sundermeyer¹,

Mousavian²,

Triebel³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Grasping unseen objects in unconstrained, cluttered environments is an essential skill for autonomous robotic manipulation. Despite recent progress in full 6-DoF grasp learning, existing approaches often consist of complex sequential pipelines that possess several potential failure points and run-times unsuitable for closed-loop grasping. Therefore, we propose an end-to-end network that efficiently generates a distribution of 6-DoF parallel-jaw grasps directly from a depth recording of a scene. Our novel grasp representation treats 3D points of the recorded point cloud as potential grasp contacts. By rooting the full 6-DoF grasp pose and width in the observed point cloud, we can reduce the dimensionality of our grasp representation to 4-DoF which greatly facilitates the learning process. Our class-agnostic approach is trained on 17 million simulated grasps and generalizes well to real world sensor data. In a robotic grasping study of unseen objects in structured clutter we achieve over 90% success rate, cutting the failure rate in half compared to a recent state-of-the-art method. Video of the real world experiments and code are available at https://research.nvidia.com/publication/ 2021-03_Contact-GraspNet%3A--Efficient.

show abstract