完美下巴标准_平行下颚抓
完美下巴標準
This article contains heuristics for following:
本文包含以下啟發式方法：
- Parallel jaw grasps. 下頜平行抓緊。
- Suction grasps. 吸氣。
- Linear push policies for improving parallel jaw grasps. 線性推動策略可改善平行顎的抓握力。
- Toppling policies for improving suction grasps. 改善吸力控制的主要政策。
Grasping is one of the fundamental subtask of a robotic manipulation pipeline. Both learning based and physics / geometry based grasping methods can benefit from grasp sampling heuristics in this article. Even if you are using a large arm farm to teach your robots the skills of grasping, you can save your robots quite a lot of time with these heuristics. This article summarizes the most common grasp sampling heuristics used in literature.
抓取是機器人操縱管線的基本子任務之一。 本文中的基于學習和基于物理/幾何的抓取方法都可以從抓取采樣啟發式方法中受益。 即使您正在使用大型武裝農場來教您的機器人掌握技巧 ，您也可以通過這些啟發式方法為您的機器人節省大量時間。 本文總結了文獻中最常見的抓取采樣啟發式方法。
Some of the common ways to use these heuristics are:
使用這些啟發式方法的一些常見方法是：
Generating labels for learning based grasp planners (offline): 6-DOF GraspNet [4] uses these samplers for evaluation with physics based simulation. Grasps that retain the object between the gripper are considered successful after a predefined shaking motion. DexNet [2][3] evaluates these grasps based on analytic quasi-static grasp wrench space (GWS) analysis. Both methods score these sampled grasps based on how good they are in resisting disturbances. These scores are used as labels for training the grasp planners.
為學習型抓手計劃者生成標簽(離線)： 6自由度GraspNet [4]使用這些采樣器進行基于物理的仿真評估。 在預定義的搖動之后，將物體保持在抓具之間的抓握被認為是成功的。 DexNet [2] [3]基于準靜態抓緊扳手空間(GWS)分析對這些抓握進行評估。 兩種方法都基于它們在抵抗干擾方面的出色程度對這些采樣的抓取力進行評分。 這些分數用作培訓掌握計劃者的標簽。
During grasp synthesis (inference): DexNet [2][3] uses these sampled grasps as seeds for Cross Entropy Method (CEM), and optimizes grasps based on predicted grasp quality from GQ-CNN (Grasp Quality Convolutional Network). Traditional geometric methods, prune these candidate grasps if they are kinematically infeasible or if they result in collision between gripper and other objects or environment. The best of these samples are picked for execution.
在抓取合成(推斷)期間： DexNet [2] [3]將這些采樣的抓取用作交叉熵方法(CEM)的種子，并基于GQ-CNN(抓取質量卷積網絡)的預測抓取質量來優化抓取。 傳統的幾何方法會修剪這些候選對象，如果它們在運動學上不可行，或者導致抓手與其他對象或環境之間發生碰撞。 從這些樣本中最好的樣本進行執行。
We will summarize the details of heuristics for each type of grippers used for manipulation.
我們將總結用于操縱的每種類型的抓取器的啟發式方法的詳細信息。
平行下顎抓 (Parallel jaw grasps)
Parallel jaw grasps jam the object between the grippers (Most often the grippers have rubber on them to increase the size of friction cones and thus the robustness of the grasp). Typically, the success of parallel jaw grasp depends on local geometry around the grasp point like if the grasp fits inside the gripper, friction btw gripper and object surface, mass of the object.
平行的下頜抓握器會夾住抓具之間的物體(大多數情況下，抓具上都帶有橡膠以增加摩擦錐的大小，從而增加抓握的堅固性)。 通常，平行下頜抓取的成功取決于抓取點周圍的局部幾何形狀，例如抓取是否適合抓取器內部，抓取器與物體表面的摩擦力，物體的質量。
Force Closure: If the contact points on the object are such that forces applied on those points don’t result in slippage and can resist gravity then force closure ( object doesn’t move with respect to the gripper ) is achieved, the grasp is considered successful.
力封閉：如果物體上的接觸點不會對物體施加力而導致打滑，并且可以抵抗重力，則可以實現力封閉(物體相對于抓具不會移動)，則應考慮抓緊成功。
Parametrization: Parallel Jaw Grasps are typically parametrized by 6-DOF pose of the gripper with initial configuration of open gripper.
參數化：平行下頜抓握通常是通過夾具的6自由度姿勢和開放式夾具的初始配置來參數化的。
Illustration shows the friction cones and forces applied by fingers at contact points on a cuboid. This illustration doesn’t account for gravity. Picture Credit: https://arxiv.org/abs/1905.00134v2該圖顯示了長方體上接觸點處的手指施加的摩擦錐和力。 此插圖未說明重力。 圖片來源： https : //arxiv.org/abs/1905.00134v2A Billion ways to grasp [1] summarizes several heuristics for parallel jaw grippers and evaluates their precision and coverage w.r.t a uniform sampler.
十億種掌握方法[1]總結了平行顎式抓爪的幾種啟發式方法，并通過統一的采樣器評估了它們的精度和覆蓋率。
Assumption: Access to the 3D triangle mesh or 3D point cloud of the object so that surface normals can be computed.
假設：訪問對象的3D三角形網格或3D點云，以便可以計算表面法線。
Here are the two most effective heuristics that are purely based on geometry:
以下是兩個完全基于幾何的最有效的啟發式方法：
Approach based samplers:
基于方法的采樣器：
These methods are characterized by approach vector of the gripper (red-dashed line) which typically aligns with normal to the palm (purple axis).
這些方法的特征在于抓手的接近向量(紅色虛線)，通常與手掌法線(紫色軸)對齊。
Approach based sampler. Picture Credit: Billion ways to Grasp [1]基于方法的采樣器。 圖片信用：十億種掌握方式[1]Pseudo code for approach based sampler:
基于方法的采樣器的偽代碼：
Antipodal based samplers:
基于對立采樣器：
These methods sample directly on the space of possible contact points and try to exploit the grasps that create force closure.
這些方法直接在可能的接觸點的空間上采樣，并嘗試利用產生力閉合的抓緊力。
Antipodal based sampler. Picture Credit: Billion ways to Grasp [1]基于對立的采樣器。 圖片信用：十億種掌握方式[1]Pseudo code for antipodal grasp sampler:
對偶采樣器的偽代碼：
Billion ways to grasp [1] evaluates grasps based on two metrics:
十億種把握方式[1]根據兩個指標評估把握：
Robust coverage: Percent of robust grasps (still successful in a small ?-neighborhood) sampled w.r.t oracle uniform sampler. This is very similar to recall.
穩健的覆蓋率：穩健的掌握率(在一個小的?鄰域中仍然成功)從oracle統一采樣器中采樣的百分比。 這與召回非常相似。
Precision: Percent of the successful grasps among the sampled.
精度：樣本中成功掌握的百分比。
As seen by the conclusion of Billion ways to grasp[1] from the tables, if you have a limited sampling budget antipodal sampling scheme provides both highest coverage and precision. However, asymptotically misses several ground truth grasps. These correspond to small scale features on objects and along the edges of objects.
從表中的“十億種方法”的結論可以看出[1]，如果您的采樣預算有限，則對映采樣方案可以提供最高的覆蓋率和精度。 然而，漸進地錯過了一些地面真理的掌握。 這些對應于對象上以及沿著對象邊緣的小比例特征。
Visual illustration of what these sampled successful grasps and robust successful grasps look like. Each point is the grasp center and notice how robust grasps are clustered around object parts that fit nicely inside the gripper.
這些采樣的成功掌握和穩健的成功掌握的視覺示意圖看起來像。 每個點都是抓地力中心，注意堅固的抓地力如何聚集在非常適合抓手內部的對象部分周圍。
Picture Credit: Billion ways to Grasp [1]圖片信用：十億種掌握方式[1]吸盤 (Suction grippers)
Suction grippers form vacuum seal on the surface of the object and if that vacuum force is sufficient to resist the gravity and external wrenches, the grasp is robust. Typically suction grasp success depends on surface porousness, local geometry, mass and payload capacity of the suction gripper. These grippers are most popular for pick and place of objects in warehouse order fulfillment. DexNet 4.0 [6] which is one of the best published bin-picking system that uses composite policy between suction and parallel jaw grasps, chooses suction grasps for about 82% of attempts.
吸氣夾具在物體表面形成真空密封，如果該真空力足以抵抗重力和外部扳手，則抓握力很強。 通常，抽吸抓取成功與否取決于抽吸抓具的表面Kong隙度，局部幾何形狀，質量和有效載荷容量。 這些抓取器最常用于在倉庫訂單履行中拾取和放置對象。 DexNet 4.0 [6]是使用率最高的垃圾收集系統之一，它在吸力和平行下顎抓地力之間采用了復合策略，大約有82％的嘗試選擇了吸力抓地力。
Parametrization: Suction grasps are typically parameterized by point p on the object surface and approach vector v as illustrated below.
參數化：吸氣抓取通常由對象表面上的點p和逼近向量v參數化 ，如下所示。
Illustration of seal formation on non-planar surface from DexNet 3.0 [3]DexNet 3.0 [3]說明了在非平面表面上形成密封的情況。Planarity Centroid Heuristic:
平面質心啟發式：
Since successful suction grasps prefer planar non-porous surfaces, these heuristics try to find sufficiently planar surfaces on the object that are closer to COM (Center of Mass). Approach vectors are chosen along the surface normal because large motion tangential to surface might result in vacuum seal breakage.
由于成功的抽吸抓取更喜歡平面的無Kong表面，因此這些啟發式方法試圖在物體上找到更靠近COM(質心)的足夠平面的表面。 沿表面法線選擇接近向量，因為與表面相切的大運動可能會導致真空密封破裂。
Pseudo code for planarity centroid heuristic:
平面性質心啟發式的偽代碼：
Some examples of successful suction grasps on 3D meshes are visualized below.
下面是3D網格上成功吸取的一些示例。
Illustrates suction grasps on diverse objects from DexNet 3.0 [3]dataset. Each point is a suction grasp sample with red → failed grasp and green → successful grasp.說明了DexNet 3.0 [3]數據集對各種對象的吸引作用。 每個點都是具有紅色→失敗抓握和綠色→成功抓握的吸力抓取樣本。DexNet 3.0 [3] evaluates suction grasps in physical robot trials based on two metrics:
DexNet 3.0 [3]根據兩個指標評估物理機器人試驗中的吸力抓地力：
Average Precision: Area under the precision / recall curve. How good is the heuristic in scoring high quality grasps ?
平均精度：精度/召回曲線下的面積。 高質量抓取得分的啟發式方法有多好？
Success Rate: Fraction of the grasps that were successful.
成功率：成功把握的分數。
As can be seen from the table above, Planarity Centroid Heuristic does quite well compared to even learnt method DexNet 3.0 [3] on basic and typical objects.
從上表可以看出，相對于基本對象和典型對象的學習方法DexNet 3.0 [3]，Planarity Centroid Heuristic的性能非常好。
Some of the failure cases of suction grasps are categorized as below:
吸力抓握的一些失敗案例分類如下：
Failure cases from DexNet 3.0 [3]. Imperceptible objects have small holes in them or have high curvature that prevents the vacuum seal and Impossible objects are porous.DexNet 3.0中的失敗案例[3]。 難以察覺的物體上有小Kong，或者曲率高，阻止了真空密封，并且不可能的物體是多Kong的。自適應采樣器： (Adaptive sampler:)
These methods use heuristics that exploit the geometry to generate seed samples (described above) and further optimize the grasp according to grasp quality metric. Most often these are blackbox optimization technique such as cross entropy method (CEM) that doesn’t exploit object geometry. Although CEM is an optimization algorithm used in many areas, I would still consider it a heuristic since it doesn’t exploit the object geometries while sampling.
這些方法使用啟發式技術，該啟發式技術利用幾何形狀生成種子樣本(如上所述)，并根據抓地質量指標進一步優化抓地力。 最常見的是黑箱優化技術，例如不利用對象幾何形狀的交叉熵方法(CEM)。 盡管CEM是許多領域中使用的優化算法，但我仍然認為它是一種啟發式方法，因為它在采樣時不會利用對象的幾何形狀。
Additional assumption: Access to grasp quality function such as DexNet 2.0 / DexNet 3.0 Grasp Quality Network (GQ-CNN) or ability to evaluate quality of grasps in realtime based on GWS.
附加假設：可訪問抓取質量功能(例如DexNet 2.0 / DexNet 3.0抓握質量網絡(GQ-CNN))或基于GWS實時評估抓握質量的能力。
交叉熵法(CEM) (Cross Entropy Method (CEM))
If you were familiar with CEM, you may have noticed the use of GMM instead of Gaussians and this is because distribution of grasps on most objects are multi-modal.
如果您熟悉CEM，則可能已經注意到使用GMM而不是高斯模型，這是因為大多數對象上的控制點分布是多模式的。
Some examples of applying CEM method to DexNet 2.0 (parallel jaw grasps )and DexNet 3.0 (suction grasps) grasp quality functions to generate most robust grasps.
將CEM方法應用于DexNet 2.0(平行下頜抓緊)和DexNet 3.0(抽吸抓緊)的一些示例可抓握質量函數以生成最可靠的抓握。
CEM method used by DexNet 2.0 [2] Marked in Black is the grasp output by CEM, which is very close to global maximum according to the robustness predictions 𝑄𝜃DexNet 2.0 [2]中用黑色標記的CEM方法是CEM的抓取輸出，根據魯棒性預測，它非常接近全局最大值𝑄𝜃 CEM method used by DexNet 3.0 [3] Also, in this case CEM method finds the best suction grasp predicted by 𝑄𝜃DexNet 3.0使用的CEM方法[3]而且，在這種情況下，CEM方法找到由predicted預測的最佳吸力抓取增加把握的機會 (Improving chances of grasping)
Sometimes neither suction grasp not parallel jaw grasp is able to pick up any object in the heap. This is mostly due to inability to perceive robust grasps (occlusion) or inability to execute the perceived grasp ( collision or kinematic infeasibility ). In those cases non-prehensile ( fancy word for non-graspable ) actions are executed to either singulate the object to expose enough clearance for parallel jaw grasps or topple the object to expose a planar surface for suction grasps.
有時，吸力抓取器和平行顎抓持器都不能夠拾取堆中的任何物體。 這主要是由于無法感知穩固的抓握(咬合)或無法執行感知的抓握(碰撞或運動學上的不可行性)。 在這些情況下，將執行非預緊(花哨詞表示不可抓握)的操作，以將對象切成單個物體以露出足夠的間隙以平行抓緊顎，或者翻倒對象以露出用于抓握的平面。
CAUTION: The following policies have not been tested on a real robot, so the results and conclusions don’t necessarily transfer.
注意：以下策略尚未在真實的機器人上進行過測試，因此結果和結論不一定會傳遞。
Parametrization: Push vector (p, q) where p = {x, y, z} starting point and q = {x’, y’, z’} is the end point.
參數化：推矢量(p，q) ，其中p = {x，y，z}的起點，而q = {x'，y'，z'}是終點。
線性推 (Linear Pushing)
Linear pushing policies typically help with separating the object heap so that parallel jaw grasps are accessible.
線性推入策略通常有助于分離對象堆，以便可以平行抓緊鉗口。
Illustration of linear pushing before (left) and after (right) in simulation (above) and real robot (below). PC: [5]模擬(上)和真實機器人(下)之前(左)和之后(右)的線性推動的示意圖。 電腦：[5]Additional assumptions: Semantic instance segmentation of the objects on the bin so that each objects position on the bin is observed. Free space segmentation of the bin is also used in the linear pushing policies for choosing the push direction.
其他假設：容器上對象的語義實例分割，以便可以觀察到每個對象在容器上的位置。 箱的自由空間分段還用于線性推動策略中，以選擇推動方向。
Free Space Policy:
自由空間政策：
Aims to separate the two closest objects in the heap by pushing them towards the free space.
旨在通過將兩個最接近的對象推向自由空間來分離它們。
Pseudo-code:
偽代碼：
Boundary Shear Policy:
邊界剪切策略：
Aims to separate two closest objects in the heap by pushing one of the objects along the boundary between the objects.
旨在通過沿對象之間的邊界推動對象之一來分離堆中兩個最接近的對象。
Pseudo-code:
偽代碼：
Facilitating Grasping [5] evaluates above policies and few others in simulation in clearing the object heaps that don’t have accessible grasps and measures the confidence gain of both grasp types. As can be seen the linear pushing policies make the parallel jaw grasps more accessible than suction grasps.
促進抓取[5]在清除沒有可訪問的抓取的對象堆時評估了上述策略，并在仿真中評估了其他策略，并評估了兩種抓取類型的置信度。 可以看出，線性推動策略使平行的下顎抓握比抽吸抓握更容易接近。
Confidence gain of both parallel jaw and suction grasping policy on according Facilitating Grasping [5]根據促進抓地力，平行顎和抽吸抓握策略的置信度增加[5] Example of before / after of linear pushing policies described above in simulated object heaps. PC: Facilitating Grasping [5].在模擬對象堆中上述線性推送策略之前/之后的示例。 PC：便于掌握[5]。單一對象倒塌 (Singulated Object Toppling)
Facilitating grasping [5] also explores policies for toppling a singulated known 3D object so that quality of suction grasp after toppling can be improved.
促進抓握[5]還探討了使單個已知3D對象發生倒塌的策略，從而可以提高倒塌后的吸取質量。
Topping to facilitate the top-down suction grasp. PC: Facilitating grasping [5]打頂，便于自上而下的吸抓。 PC：促進抓握[5]Assumptions: Known 3D object with known transition distribution of stable resting poses P[x_{t+1}|x_t, u_t] and access to suction grasp quality function V_s(x_t).
假設：已知的3D對象具有穩定的靜止姿勢P [x_ {t + 1} | x_t，u_t]的已知過渡分布，并可以訪問吸力抓握質量函數V_s(x_t)。
Max Height Policy:
最大高度政策：
Highest possible point on the object that has surface normal within 15 degree of the supporting plane normal. This policy only gets executed if V_s(x_{t+1}) > V_s(x_t).
表面法線在支撐平面法線15度以內的物體上的最高點。 僅當V_s(x_ {t + 1})> V_s(x_t)時才執行此策略。
Greedy Policy:
貪婪政策：
Pick the action that makes the expected suction grasp more accessible.
選擇使預期的吸力抓握更容易接近的動作。
Facilitating grasping [5] evaluates these policies in simulation and compares against a policy that runs complete value iteration based on P[x_{t+1}|x_t, u_t] and Vs(x_t).
便于掌握[5]在仿真中評估這些策略，并與基于P [x_ {t + 1} | x_t，u_t]和Vs(x_t)運行完整值迭代的策略進行比較。
The greedy toppling policy does fairly well compared to best performing value iteration with much less runtime PC: [5]與運行次數較少的PC相比，貪婪的崩潰策略與性能最佳的值迭代相比效果相當好：[5]Conclusion: This post explored different subtasks used for grasping and several effective heuristics for them. Please explore the references for more details on learning based / more effective policies. These heuristics are meant to provide intuition on each of the grasping subtasks and how they measure up to some of the more advanced methods.
結論：這篇文章探討了用于掌握的不同子任務以及針對它們的幾種有效啟發式方法。 請瀏覽參考資料，以獲取更多有關基于學習/更有效政策的詳細信息。 這些試探法旨在為每個掌握的子任務提供直覺，以及它們如何衡量某些更高級的方法。
翻譯自: https://medium.com/@darshanhegde_5567/heuristics-for-robotic-grasping-c28dbb90bce1
完美下巴標準
總結
以上是生活随笔為你收集整理的完美下巴标准_平行下颚抓的全部內容，希望文章能夠幫你解決所遇到的問題。
- 上一篇： 海外观众热评《流浪地球2》：中国科幻片惊
- 下一篇： IDC：2022 年中国智能手机市场出货