An official website of the United States government
Pose estimation is a basic module in many robot manipulation pipelines. Estimating the pose of objects in the environment can be useful for grasping, motion planning, or manipulation. However, current state-of-the-art methods for pose estimation either rely on large annotated training sets or simulated data. Further, the long training times for these methods prohibit quick interaction with novel objects. To address these issues, we introduce a novel method for zero-shot object pose estimation in clutter. Our approach uses a hypothesis generation and scoring framework, with a focus on learning a scoring function that generalizes to objects not used for training. We achieve zero-shot generalization by rating hypotheses as a function of unordered point differences. We evaluate our method on challenging datasets with both textured and untextured objects in cluttered scenes and demonstrate that our method significantly outperforms previous methods on this task. We also demonstrate how our system can be used by quickly scanning and building a model of a novel object, which can immediately be used by our method for pose estimation. Our work allows users to estimate the pose of novel objects without requiring any retraining.
more »
« less
CollisionIK: A Per-Instant Pose Optimization Method for Generating Robot Motions with Environment Collision Avoidance
In this work, we present a per-instant pose optimization method that can generate configurations that achieve specified pose or motion objectives as best as possible over a sequence of solutions, while also simultaneously avoiding collisions with static or dynamic obstacles in the environment. We cast our method as a weighted sum non-linear constrained optimization-based IK problem where each term in the objective function encodes a particular pose objective. We demonstrate how to effectively incorporate environment collision avoidance as a single term in this multi-objective, optimization-based IK structure, and provide solutions for how to spatially represent and organize external environments such that data can be efficiently passed to a real-time, performance-critical optimization loop. We demonstrate the effectiveness of our method by comparing it to various state-of-the-art methods in a testbed of simulation experiments and discuss the implications of our work based on our results.
more »
« less
- Award ID(s):
- 1830242
- PAR ID:
- 10340410
- Date Published:
- Journal Name:
- IEEE International Conference on Robotics and Automation (ICRA)
- Page Range / eLocation ID:
- 9995 to 10001
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Finding diverse and representative Pareto solutions from the Pareto front is a key challenge in multi-objective optimization (MOO). In this work, we propose a novel gradient-based algorithm for profiling Pareto front by using Stein variational gradient descent (SVGD). We also provide a counterpart of our method based on Langevin dynamics. Our methods iteratively update a set of points in a parallel fashion to push them towards the Pareto front using multiple gradient descent, while encouraging the diversity between the particles by using the repulsive force mechanism in SVGD, or diffusion noise in Langevin dynamics. Compared with existing gradient-based methods that require predefined preference functions, our method can work efficiently in high dimensional problems, and can obtain more diverse solutions evenly distributed in the Pareto front. Moreover, our methods are theoretically guaranteed to converge to the Pareto front. We demonstrate the effectiveness of our method, especially the SVGD algorithm, through extensive experiments, showing its superiority over existing gradient-based algorithms.more » « less
-
We introduce Visual Inverse Kinematics (VIK), which finds kinematically feasible joint configurations that satisfy vision-based constraints, bridging the gap between inverse kinematics (IK) and visual servoing (VS). Unlike IK, no explicit end-effector pose is given, and unlike VS, exact image measurements may not be available. In this work, we develop a formulation of the VIK problem with a field of view (FoV) constraint, enforcing the visibility of an object from a camera on the robot. Our proposed solution introduces a virtual kinematic chain that connects the physical robot and the object, transforming the FoV constraint into a joint angle kinematic constraint. Along the way, we introduce multiple vision-based cost functions to fulfill different objectives. We solve this formulation of the VIK problem using a method that involves a semidefinite program (SDP) constraint followed by a rank minimization algorithm. The performance of this method for solving the VIK problem is validated through simulations.more » « less
-
Inverse kinematics (IK) is an important problem in robot control and motion planning; however, the nonlinearity of the map from joint angles to robot configurations makes the problem nonconvex. In this paper, we propose an inverse kinematics solver that works in the space of rotation matrices of the link reference frames rather than joint angles. To overcome the nonlinearity of the manifold of rotation matrices $$\mathbf{SO}(3)$$, we propose a semidefinite programming (SDP) relaxation of the kinematic constraints followed by a fixed-trace rank minimization via maximization of a convex function. Along the way, we show that the feasible set of an IK problem is exactly the intersection of a convex set and fixed-trace rank-1 matrices. Thanks to the use of matrices with fixed trace, our algorithm to obtain rank-1 solutions has guaranteed local convergence. Unlike some traditional solvers, our method does not require an initial guess, and can be applied to robots with closed kinematic chains without ad-hoc modifications such as splitting the kinematic chain. Compared to other work that performs SDP relaxation for IK problems, our formulation is simpler, and uses variables with smaller sizes. We validate our approach via simulations on a closed kinematic chain constituted by two robotic arms holding a box, comparing against a standard IK method.more » « less
-
Domain-specific systems-on-chip (DSSoCs) combine general-purpose processors and specialized hardware accelerators to improve performance and energy efficiency for a specific domain. The optimal allocation of tasks to processing elements (PEs) with minimal runtime overheads is crucial to achieving this potential. However, this problem remains challenging as prior approaches suffer from non-optimal scheduling decisions or significant runtime overheads. Moreover, existing techniques focus on a single optimization objective, such as maximizing performance. This work proposes DTRL, a decision-tree-based multi-objective reinforcement learning technique for runtime task scheduling in DSSoCs. DTRL trains a single global differentiable decision tree (DDT) policy that covers the entire objective space quantified by a preference vector. Our extensive experimental evaluations using our novel reinforcement learning environment demonstrate that DTRL captures the trade-off between execution time and power consumption, thereby generating a Pareto set of solutions using a single policy. Furthermore, comparison with state-of-the-art heuristic–, optimization–, and machine learning-based schedulers shows that DTRL achieves up to 9× higher performance and up to 3.08× reduction in energy consumption. The trained DDT policy achieves 120 ns inference latency on Xilinx Zynq ZCU102 FPGA at 1.2 GHz, resulting in negligible runtime overheads. Evaluation on the same hardware shows that DTRL achieves up to 16% higher performance than a state-of-the-art heuristic scheduler.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICRA48506.2021.9561505
