Hong Kong, May 31 2014, at ICRA
international workshop on
Autonomous Grasping and Manipulation: An Open Challenge

Thanks everyone for a great day!

AG&M 2014: Motivation

Research in robot grasping has experienced a massive shift in recent years. Early research into the field focused on synthesizing grasps analytically, using precise and accurate models of the objects to be grasped. Although these approaches are well-suited for grasping objects in industrial scenarios, such as on an assembly line, they are not easily applicable to unstructured environments like households or hospitals.

During the past fifteen years, grasping research has shifted to methods that can cope with novel objects and partial/noisy perceptual data. The challenges posed by grasping in these situations have led to the development of a wide range of new algorithms for selecting, executing, and evaluating grasps. In parallel to the progress made on the software level, new robot hands and sensors have also been designed for operating in everyday environments.

The first aim of the workshop is to report progress in the large variety of grasping and manipulation methods. The second aim of the workshop is to discuss the increasing difficulty in comparing the practical applicability of all the new algorithms and hardware that appear each month. Comparing different methodologies in a fair manner is difficult. The success of a grasp depends on many factors, such as the type of robot hand/gripper, the immediate environment around the object, and the properties of the objects being grasped. Different methods might also assume different prior knowledge regarding the object, or rely on the robot being equipped with certain sensors. The lack of suitable means of comparison has become a serious concern. The workshop will serve as a platform to discuss the role of benchmarking in grasping and manipulation. In particular, we will animate a discussion on the pros, cons, benefits and pitfalls of benchmarking via a periodic community-organized grasping/manipulation challenge.

Invited Speakers

  1. Pieter Abbeel (University of California, Berkeley)
  2. Oliver Brock (TU Berlin)
  3. Nicholas Hudson (JPL)
  4. Manuel Lopes (INRIA Bordeaux Sud-Ouest)
  5. Toru Omata (Tokyo Institute of Technology)
  6. Robert Platt (Northeastern)
  7. Ashutosh Saxena (Cornell University)


The workshop will take place on Saturday 31st of May 2014. The program of the day is as follows:

Session 1: 9:00–10:30 (1:30 hours)

9:00–9:30: Keynote
Learning to Manipulate from Demonstrations through the Use of Non-Rigid Registration
Pieter Abbeel (University of California, Berkeley)
9:30–10:00: Keynote
Semi-autonomous third-hand robot
Manuel Lopes (INRIA Bordeaux Sud-Ouest)
10:00–10:30: Spotlight presentations of all posters (2 minutes per poster)


Session 2: 10:50–12:30 (1:40 hours)

10:50–11:20: Poster Session 1
(all posters)
11:20–11:50: Keynote
Title to be announced shortly
Nicholas Hudson (JPL)
11:50–12:20: Keynote
Robot hand design for grasping and manipulation of a variety of objects
Toru Omata (Tokyo Institute of Technology)


Session 3: 14:00–15:30 (1:30 hours)

14:00–14:20: Short Talks
Renaud Detry and Oliver Kroemer
14:20–14:50: Keynote
Perception for manipulation
Robert Platt (Northeastern)
14:50–15:15: Keynote
Robot hand design for grasping and manipulation of a variety of objects
Toru Omata (Tokyo Institute of Technology)


Session 4: 15:50–17:30 (1:40 hours)

15:50–16:05: Poster Session 2
(all posters)
16:05–16:35: Keynote
Soft Grasping and Manipulation
Oliver Brock (TU Berlin)
16:35–17:00: Keynote
PlanIt: Scaling the Learning for Grasping and Path Planning
Ashutosh Saxena (Cornell University)

17:00–17:30: Discussion with the panel of invited speakers.

Poster Session

  1. Similar Part Rearrangement in Cluttered Environments, Athanasios Krontiris, Rahul Shome, Andrew Dobson, Andrew Kimmel, Isaac Yochelson and Kostas Bekris [Download video]
  2. Adaptive contact point estimation for autonomous tool manipulation, Francisco Vina, Christian Smith, Danica Kragic and Yiannis Karayiannidis
  3. A Dataset of Human Manipulation Actions, Alessandro Pieropan, Giampiero Salvi, Karl Pauwels and Hedvig Kjellström [Download video]
  4. On Object Affordances, Alessandro Pieropan, Carl Henrik Ek and Hedvig Kjellström [Download video]
  5. Rotation and Translation Invariant Object Recognition with Tactile Sensors While Grasping, Shan Luo, Kaspar Althoefer and Hongbin Liu
  6. How to Think about Designing and Controlling Robotic Hands, Leif P Jentoft, Qian Wan and Robert D. Howe [Download video]
  7. Hierarchical Fingertip Space for Synthesizing Adaptable Fingertip Grasps, Kaiyu Hang, Miao Li, Johannes Andreas Stork, Yasemin Bekiroglu, Aude Billard and Danica Kragic
  8. Finger Surface Following Control through Intrinsic Contact Sensing, Junghwan Back, Hongbin Liu and Kaspar Althoefer [Download video]
  9. A Visuo-haptic Sensor for the Exploration of Deformable Objects, Nicolas Alt and Eckehard Steinbach
  10. Improving Grasp Robustness via In-Hand Manipulation with Active Surfaces, Robert Krug, Todor Stoyanov, Manuel Bonilla, Vinicio Tincani, Narunas Vaskevicius, Gualtiero Fantoni, Andreas Birk, Achim Lilienthal and Antonio Bicchi [Download video]
  11. A Roadmap Towards Intelligent and Autonomous Object Manipulation for Assembly Tasks, Athanasios Polydoros, Lazaros Nalpantidis and Volker Krüger
  12. Unsupervised Learning of Spatio-Temporal Features for Tactile Data, Marianna Madry, Liefeng Bo, Danica Kragic and Dieter Fox

Call for Contributions

The workshop will be held on May 31 as part of the IEEE International Conference on Robotics and Automation (ICRA 2014) in Hong Kong, China. We warmly welcome the submission of extended abstracts of 1-2 pages on novel work or work in progress. Abstracts will be (single-blind) reviewed on the basis of relevance, significance, and clarity. Accepted contributions will be presented as posters during the workshop. The authors may also be given the chance to additionally give a short spotlight presentation of their work. The workshop proceedings will be published online, on the AG&M website.

Format 1–2 pages, with optional video
Submission deadline April 30, 2014 (23:59 CET)
Notification of acceptance May 7, 2014
Camera-ready May 17, 2014

Extended abstracts should be formatted according to the manuscript preparation guidelines and should be submitted in PDF via EasyChair. PDF file size is limited to 10MB.

Authors are encouraged to submit a live demo or a video showcasing their work. Accompanying videos can also be uploaded via the submission system. We accept the following formats: MPEG-1 stream within a .MPG container, or MPEG-4 stream (H.264 recommended) within a .MP4 container. The maximum file size is 20MB.

Contributions are encouraged in the following areas:

  • Benchmarking robot grasping/manipulation
  • Task-specific grasping/manipulation
  • Grasping/manipulation in cluttered environments
  • Grasping/manipulation with compliant robots
  • Robot hand design
  • Tactile sensing for grasping/manipulation
  • Grasping/manipulation non-rigid objects
  • Best practices in robot grasping/manipulation research
  • Whole-arm grasping/manipulation
  • Bimanual/multi-handed grasping/manipulation
  • Adapting grasps to changing environments
  • Grasping with ambiguous sensory signals
  • Modeling uncertainty in environments and actions
  • Using multi-sensory object representations for grasping
  • Learning from human demonstrations
  • Grasping in simulation vs on a real system
  • Estimating task-relevant features of objects
  • Grasp synergies
  • Learning grasps through self-improvement methods
  • Learning from insights into human grasping
  • Grasping articulated objects
  • Open problems in grasping and manipulation
  • Code and dataset sharing

Workshop Organizers

Renaud Detry, University of Liege, Belgium
Oliver Kroemer, Technische Universitaet Darmstadt
Danica Kragic, Royal Institute of Technology (KTH)


For further inquiries, please email:, or contact one of the organisers.
Valid HTML5 and CSS
Renaud Detry, Oliver Kroemer, Danica Kragic