Online Planning for Target Object Search in Clutter under Partial Observability

Xiao, Yuchen; Katt, Sammie; Pas, Andreas ten; Chen, Shengjian; Amato, Christopher

doi:10.1109/icra.2019.8793494

Cited by 68 publications

(58 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xiao et al [65] achieved a high accuracy for the pick-and-place task in a cluttered environment with the Parameterized Action Partially Observable Monte-Carlo Planning (PA-POMCP). The system approximated the utility of available actions based on the current belief of the agent about the environment.…”

Section: State Of Research-complete Pick-and-place Taskmentioning

confidence: 99%

Reinforcement Learning for Pick and Place Operations in Robotics: A Survey

2021

View full text Add to dashboard Cite

The field of robotics has been rapidly developing in recent years, and the work related to training robotic agents with reinforcement learning has been a major focus of research. This survey reviews the application of reinforcement learning for pick-and-place operations, a task that a logistics robot can be trained to complete without support from a robotics engineer. To introduce this topic, we first review the fundamentals of reinforcement learning and various methods of policy optimization, such as value iteration and policy search. Next, factors which have an impact on the pick-and-place task, such as reward shaping, imitation learning, pose estimation, and simulation environment are examined. Following the review of the fundamentals and key factors for reinforcement learning, we present an extensive review of all methods implemented by researchers in the field to date. The strengths and weaknesses of each method from literature are discussed, and details about the contribution of each manuscript to the field are reviewed. The concluding critical discussion of the available literature, and the summary of open problems indicates that experiment validation, model generalization, and grasp pose selection are topics that require additional research.

show abstract

Section: State Of Research-complete Pick-and-place Taskmentioning

confidence: 99%

Reinforcement Learning for Pick and Place Operations in Robotics: A Survey

2021

View full text Add to dashboard Cite

show abstract

“…One approach to online planning is to use Monte-Carlo sampling [17], [18] to explore likely outcomes of various actions. These methods have been successfully applied to robotic planning tasks such as grasping in clutter [19], non-prehensile rearrangement [20], and object search [21]. However, the hybrid action space in our application is too high-dimensional for uninformed action sampling to generate useful actions.…”

Section: Related Workmentioning

confidence: 99%

“…There are many approaches for representing and updating a belief such as joint, unscented Kalman filtering [23], [7], factoring the belief into independent distributions per object [15], [25], and maintaining a particle filter, which represents the belief as a set of weighted samples [17], [18], [19], [21]. Many approaches use a different belief representation when planning versus when filtering.…”

Section: Related Workmentioning

confidence: 99%

Online Replanning in Belief Space for Partially Observable Task and Motion Problems

Garrett¹,

Paxton²,

Lozano-Pérez³

et al. 2020

2020 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

“…The grasping community considered the problem of planning and executing grasps on a pile of cluttered objects until all objects have been cleared. Depending on the assumed prior knowledge these methods can be considered modelbased [18][19][20] or model-free approaches [1,3,4,[21][22][23][24][25]. The latter use only images to decide on the best grasping action for a pile of objects.…”

Section: Related Workmentioning

confidence: 99%

Visuomotor Mechanical Search: Learning to Retrieve Target Objects in Clutter

Kurenkov

Taglic

Kulkarni

et al. 2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

When searching for objects in cluttered environments, it is often necessary to perform complex interactions in order to move occluding objects out of the way and fully reveal the object of interest and make it graspable. Due to the complexity of the physics involved and the lack of accurate models of the clutter, planning and controlling precise predefined interactions with accurate outcome is extremely hard, when not impossible. In problems where accurate (forward) models are lacking, Deep Reinforcement Learning (RL) has shown to be a viable solution to map observations (e.g. images) to good interactions in the form of close-loop visuomotor policies. However, Deep RL is sample inefficient and fails when applied directly to the problem of unoccluding objects based on images. In this work we present a novel Deep RL procedure that combines i) teacheraided exploration, ii) a critic with privileged information, and iii) mid-level representations, resulting in sample efficient and effective learning for the problem of uncovering a target object occluded by a heap of unknown objects. Our experiments show that our approach trains faster and converges to more efficient uncovering solutions than baselines and ablations, and that our uncovering policies lead to an average improvement in the graspability of the target object, facilitating downstream retrieval applications.

show abstract

Online Planning for Target Object Search in Clutter under Partial Observability

Cited by 68 publications

References 15 publications

Reinforcement Learning for Pick and Place Operations in Robotics: A Survey

Reinforcement Learning for Pick and Place Operations in Robotics: A Survey

Online Replanning in Belief Space for Partially Observable Task and Motion Problems

Visuomotor Mechanical Search: Learning to Retrieve Target Objects in Clutter

Contact Info

Product

Resources

About