Learning to Throw Objects Safely in Multi-Obstacle Environments

• URL: http://arxiv.org/abs/2607.06388v1
• Date: Tue, 07 Jul 2026 15:24:12 GMT
• Title: Learning to Throw Objects Safely in Multi-Obstacle Environments
• Abstract summary: Existing approaches, such as TossingBot, learn throwing strategies from visual input but assume obstacle-free settings.<n>We introduce a potential field state representation that compactly encodes both basket attraction and obstacle repulsion on a fixed-size grid.<n>We show that PFR provides a practical and robust representation for safe and efficient robotic throwing in unstructured environments.
• Score: 14.544049936179071
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Robotic throwing enables fast and efficient object placement beyond the robot's immediate workspace, but reliable throwing in cluttered environments remains underexplored. Existing approaches, such as TossingBot, learn throwing strategies from visual input but assume obstacle-free settings. In this paper, we address the problem of throwing objects into a target basket while avoiding obstacles placed randomly in the scene. We introduce a potential field state representation that compactly encodes both basket attraction and obstacle repulsion on a fixed-size grid, enabling reinforcement learning (RL) policies to generalize across arbitrary numbers and configurations of obstacles. The policy is initialized from kinesthetic demonstrations and optimized in simulation using three state-of-the-art RL algorithms (SAC, DDPG, TD3). Among these, SAC achieves the most consistent performance across scenarios. We compare the potential field representation against explicit state encodings and demonstrate that it achieves higher success rates and better scalability to unseen obstacle configurations. Real-robot experiments with unseen throwable objects confirm robust sim-to-real transfer, achieving up to $90\%$ success in cluttered scenes. These results demonstrate that PFR provides a practical and robust representation for safe and efficient robotic throwing in unstructured environments. A video showcasing our experiments is available at: https://youtu.be/ZZnJf8ua2dE

Related papers

• GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments [63.222920701596564]
  Training embodied agents in the real world requires skilled operators and expensive hardware.<n> Simulation environments offer a compelling alternative by enabling large-scale, cost-effective data augmentation.<n>Fastly constructing high-fidelity simulation scenes with a minimal sim-to-real gap has become a critical objective in robot learning.
  arXiv  Detail & Related papers  (2026-06-16T05:00:42Z)
• Trans2Occ: Voxel Occupancy Estimation and Grasp for Transparent Objects from Simulation to Reality [125.76063573012853]
  We present a framework for transparent object perception and manipulation based on single-view RGB input.<n>Our approach predicts voxel-space occupancy directly from a single image, providing a geometry-aware representation that supports downstream robotic grasping.
  arXiv  Detail & Related papers  (2026-06-01T06:59:13Z)
• Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors [51.096845970243855]
  Whole-body Humanoid-Object Interaction (HOI) is bottlenecked by the scarcity of high-fidelity 3D data.<n>We propose Imagine2Real, a zero-shot HOI framework for flexible, geometry-free interaction.
  arXiv  Detail & Related papers  (2026-05-21T10:15:39Z)
• AdaClearGrasp: Learning Adaptive Clearing for Zero-Shot Robust Dexterous Grasping in Densely Cluttered Environments [31.097251477695497]
  AdaClearGrasp is a closed-loop decision-execution framework for adaptive clearing and zero-shot dexterous grasping.<n>A pretrained vision-language model (VLM) interprets visual observations and language task descriptions to reason about grasp interference.<n>Visual feedback monitors outcomes and triggers replanning upon failures, forming a closed-loop correction mechanism.
  arXiv  Detail & Related papers  (2026-03-11T10:24:20Z)
• Object-centric 3D Motion Field for Robot Learning from Human Videos [56.9436352861611]
  We propose to use object-centric 3D motion field to represent actions for robot learning from human videos.<n>We present a novel framework for extracting this representation from videos for zero-shot control.<n> Experiments show that our method reduces 3D motion estimation error by over 50% compared to the latest method.
  arXiv  Detail & Related papers  (2025-06-04T17:59:06Z)
• Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments [0.3565151496245486]
  We propose a method for effectively grasping in cluttered bin-picking environments.<n>We utilize a multi-functional gripper that combines both suction and finger grasping.<n>We also present an active gripper adaptation strategy to minimize collisions between the gripper hardware and the surrounding environment.
  arXiv  Detail & Related papers  (2025-04-02T16:12:28Z)
• IMPACT: Intelligent Motion Planning with Acceptable Contact Trajectories via Vision-Language Models [3.3871564496652335]
  IMPACT is a novel motion planning framework that uses Vision-Language Models to infer environment semantics.<n>Our results over 3200 simulation and 200 real-world trials suggest that IMPACT enables efficient contact-rich motion planning in cluttered settings.
  arXiv  Detail & Related papers  (2025-03-13T07:09:00Z)
• FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real [25.60751532514627]
  Generalizable object fetching in cluttered scenes remains a fundamental and application-critical challenge in embodied AI.<n>FetchBot is a sim-to-real framework for this challenge.<n>It achieves an average real-world success rate of 89.95%, significantly outperforming prior methods.
  arXiv  Detail & Related papers  (2025-02-25T06:32:42Z)
• Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination [12.548355269509882]
  This paper presents a new class of predictive safety filter that continually plays out hypothetical matches between its simulation-trained safety strategy and a virtual adversary.<n>We demonstrate the scalability and robustness of the approach with a first-of-its-kind full-order safety filter for (36-D) quadrupedal dynamics.
  arXiv  Detail & Related papers  (2024-05-01T20:21:44Z)
• RPMArt: Towards Robust Perception and Manipulation for Articulated Objects [56.73978941406907]
  We propose a framework towards Robust Perception and Manipulation for Articulated Objects ( RPMArt) RPMArt learns to estimate the articulation parameters and manipulate the articulation part from the noisy point cloud. We introduce an articulation-aware classification scheme to enhance its ability for sim-to-real transfer.
  arXiv  Detail & Related papers  (2024-03-24T05:55:39Z)
• Unified Control Framework for Real-Time Interception and Obstacle Avoidance of Fast-Moving Objects with Diffusion Variational Autoencoder [2.5642257132861923]
  Real-time interception of fast-moving objects by robotic arms in dynamic environments poses a formidable challenge. This paper introduces a unified control framework to address the challenge by simultaneously intercepting dynamic objects and avoiding moving obstacles.
  arXiv  Detail & Related papers  (2022-09-27T18:46:52Z)
• Nonprehensile Riemannian Motion Predictive Control [57.295751294224765]
  We introduce a novel Real-to-Sim reward analysis technique to reliably imagine and predict the outcome of taking possible actions for a real robotic platform. We produce a closed-loop controller to reactively push objects in a continuous action space. We observe that RMPC is robust in cluttered as well as occluded environments and outperforms the baselines.
  arXiv  Detail & Related papers  (2021-11-15T18:50:04Z)

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.