Learning to Play Cup-and-Ball with Noisy Camera Observations

• URL: http://arxiv.org/abs/2007.09562v1
• Date: Sun, 19 Jul 2020 02:22:36 GMT
• Title: Learning to Play Cup-and-Ball with Noisy Camera Observations
• Authors: Monimoy Bujarbaruah, Tony Zheng, Akhil Shetty, Martin Sehr, Francesco Borrelli
• Abstract summary: We present a learning model based control strategy for the cup-and-ball game. A Universal Robots UR5e manipulator arm learns to catch a ball in one of the cups on a Kendama.
• Score: 2.6931502677545947
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Playing the cup-and-ball game is an intriguing task for robotics research since it abstracts important problem characteristics including system nonlinearity, contact forces and precise positioning as terminal goal. In this paper, we present a learning model based control strategy for the cup-and-ball game, where a Universal Robots UR5e manipulator arm learns to catch a ball in one of the cups on a Kendama. Our control problem is divided into two sub-tasks, namely $(i)$ swinging the ball up in a constrained motion, and $(ii)$ catching the free-falling ball. The swing-up trajectory is computed offline, and applied in open-loop to the arm. Subsequently, a convex optimization problem is solved online during the ball's free-fall to control the manipulator and catch the ball. The controller utilizes noisy position feedback of the ball from an Intel RealSense D435 depth camera. We propose a novel iterative framework, where data is used to learn the support of the camera noise distribution iteratively in order to update the control policy. The probability of a catch with a fixed policy is computed empirically with a user specified number of roll-outs. Our design guarantees that probability of the catch increases in the limit, as the learned support nears the true support of the camera noise distribution. High-fidelity Mujoco simulations and preliminary experimental results support our theoretical analysis.

Related papers

• Table tennis ball spin estimation with an event camera [11.735290341808064]
  In table tennis, the combination of high velocity and spin renders traditional low frame rate cameras inadequate. We present the first method for table tennis spin estimation using an event camera. We achieve a spin magnitude mean error of $10.7 pm 17.3$ rps and a spin axis mean error of $32.9 pm 38.2deg$ in real time for a flying ball.
  arXiv  Detail & Related papers  (2024-04-15T15:36:38Z)
• Ball Trajectory Inference from Multi-Agent Sports Contexts Using Set Transformer and Hierarchical Bi-LSTM [18.884300680050316]
  This paper proposes an inference framework of ball trajectory from player trajectories as a cost-efficient alternative to ball tracking. The experimental results show that our model provides natural and accurate trajectories as well as admissible player ball possession at the same time. We suggest several practical applications of our framework including missing trajectory imputation, semi-automated pass annotation, automated zoom-in for match broadcasting, and calculating possession-wise running performance metrics.
  arXiv  Detail & Related papers  (2023-06-14T02:19:59Z)
• EV-Catcher: High-Speed Object Catching Using Low-latency Event-based Neural Networks [107.62975594230687]
  We demonstrate an application where event cameras excel: accurately estimating the impact location of fast-moving objects. We introduce a lightweight event representation called Binary Event History Image (BEHI) to encode event data at low latency. We show that the system is capable of achieving a success rate of 81% in catching balls targeted at different locations, with a velocity of up to 13 m/s even on compute-constrained embedded platforms.
  arXiv  Detail & Related papers  (2023-04-14T15:23:28Z)
• DribbleBot: Dynamic Legged Manipulation in the Wild [10.29780236909404]
  DribbleBot is a legged robotic system that can dribble a soccer ball under the same real-world conditions as humans (i.e., in-the-wild) We adopt the paradigm of training policies in simulation using reinforcement learning and transferring them into the real world.
  arXiv  Detail & Related papers  (2023-04-03T17:26:09Z)
• Deep-Learning-Based Computer Vision Approach For The Segmentation Of Ball Deliveries And Tracking In Cricket [4.021584094339975]
  This paper presents an approach to segment and extract video shots in which only the ball is being delivered. Object detection models are applied to reach a high level of accuracy in terms of correctly extracting video shots. Ball tracking in these video shots is also done using a separate RetinaNet model as a sample of the usefulness of the proposed dataset.
  arXiv  Detail & Related papers  (2022-11-22T04:55:58Z)
• Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot [76.04391023228081]
  We address the problem of enabling quadrupedal robots to perform precise shooting skills in the real world using reinforcement learning. We propose a hierarchical framework that leverages deep reinforcement learning to train a robust motion control policy. We deploy the proposed framework on an A1 quadrupedal robot and enable it to accurately shoot the ball to random targets in the real world.
  arXiv  Detail & Related papers  (2022-08-01T22:34:51Z)
• SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos [62.686484228479095]
  We propose a novel dataset for multiple object tracking composed of 200 sequences of 30s each. The dataset is fully annotated with bounding boxes and tracklet IDs. Our analysis shows that multiple player, referee and ball tracking in soccer videos is far from being solved.
  arXiv  Detail & Related papers  (2022-04-14T12:22:12Z)
• Ball 3D localization from a single calibrated image [1.2891210250935146]
  We propose to address the task on a single image by estimating ball diameter in pixels and use the knowledge of real ball diameter in meters. This approach is suitable for any game situation where the ball is (even partly) visible. validations on 3 basketball datasets reveals that our model gives remarkable predictions on ball 3D localization.
  arXiv  Detail & Related papers  (2022-03-30T19:38:14Z)
• Monocular Visual Analysis for Electronic Line Calling of Tennis Games [57.14812636359967]
  Electronic Line Calling is an auxiliary referee system used for tennis matches based on binocular vision technology. We propose a monocular vision technology based ELC method. We find out whether the bouncing point of the ball is out of bounds or not according to the relative position between the bouncing point and the court side line in the two dimensional image.
  arXiv  Detail & Related papers  (2021-07-20T04:23:11Z)
• Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds [62.013872787987054]
  We propose a new method for learning closed-loop control policies for 6D grasping. Our policy takes a segmented point cloud of an object from an egocentric camera as input, and outputs continuous 6D control actions of the robot gripper for grasping the object.
  arXiv  Detail & Related papers  (2020-10-02T07:42:00Z)
• Disentangling Controllable Object through Video Prediction Improves Visual Reinforcement Learning [82.25034245150582]
  In many vision-based reinforcement learning problems, the agent controls a movable object in its visual field. We propose an end-to-end learning framework to disentangle the controllable object from the observation signal. The disentangled representation is shown to be useful for RL as additional observation channels to the agent.
  arXiv  Detail & Related papers  (2020-02-21T05:43:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.