A new approach to combined symbolic-geometric backtracking in the context of human-robot interaction

Silva, Lavindra de; Gharbi, Mamoun; Pandey, Amit Kumar; Alami, Rachid

doi:10.1109/icra.2014.6907403

Cited by 10 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can be related to well known need to deal with the anchoring problem in order to fill the gap between the levels [19]. Those relations are named "Shared Literals" (as in [6]) since they are generated by the geometric level and exploited by the symbolic planner.…”

Section: Related Workmentioning

confidence: 98%

“…In [6], the approach is different since the symbolic planner creates multiple instances for the same action (if a geometric refinement is needed) and backtracks on this instances, which are in fact, different geometric alternatives for the same symbolic action. If an actions is successfully refined, geometric effects, the shared literals, are computed.…”

Section: A Previous Algorithmsmentioning

confidence: 98%

“…More recently we focused on a complementary approach [5], [6]: exploiting the capacity of the Hierarchical Task Network (HTN) [23] techniques to encode domain knowledge and developing a geometric planner capable of planning actions with several levels of abstractions, opening to more elaborate action instantiations. Such a combination provides several key features: a clean interface which corresponds to the anchoring problem and allows to better exhibit and master the links between the incremental processes of producing the symbolic plan and its geometric counterpart.…”

Section: A Previous Algorithmsmentioning

confidence: 99%

“…In a multi-agent, human-aware context, the action effects and their costs cannot be computed at symbolic level, especially while taking into account the human comfort and preferences [4]: the interleaving between symbolic and geometric planning becomes mandatory. This paper reports on the extensions of a planner we have already presented in [5], [6]. We provide details on how the ramification problem is tackled and present a number of extensions specially dedicated to the improvement of the plan search: (1) a set of high level geometric constraints, (2) the ability to encode domain-expert knowledge at both levels, (3) well-informed cost estimation of actions and (4) the ability of the geometric planner to provide several instantiations of the same action.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Combining symbolic and geometric planning to synthesize human-aware plans: toward more efficient combined search

Gharbi

Lallement

Alami

2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

We are combining symbolic and geometric planning to synthesize human-aware plans in order to deal with the complex and highly intricate planning problems induced by Human-Robot collaborative object manipulation.In this paper, we summarize our previous contributionsrefining symbolic actions at geometric level, during the symbolic planning, in order to assess their feasibility and computing the geometric side effects-, then we present the current contributions meant to tighten the cooperation between the symbolic planning and the geometric planning: the symbolic planner helps the geometric one by providing it with constraints and domain-expert knowledge making the geometric planner more efficient, and the geometric planner helps the symbolic one to find the best plan based on social costs computed at geometric level.We also propose different examples, highlighting the interest of such cooperation between the planners in simulation and on our PR2 robot.

show abstract

Section: Related Workmentioning

confidence: 98%

Section: A Previous Algorithmsmentioning

confidence: 98%

Section: A Previous Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Combining symbolic and geometric planning to synthesize human-aware plans: toward more efficient combined search

Gharbi

Lallement

Alami

2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hierarchical Planning in the Now (HPN) (Kaelbling and Lozano-Pérez, 2011, 2013) interleaves planning and execution, reducing search depth but requiring reversible actions when backtracking. Several related methods (de Silva et al, 2014, 2013a,b; Gharbi et al, 2015) extend hierarchical task networks (HTNs) (Erol et al, 1994) with geometric primitives, using shared literals to control backtracking between the task and motion layer. Srivastava et al (2014) interfaced off-the-shelf task planners with an optimization-based motion planner (Schulman et al, 2014) using a heuristic to remove potentially interfering objects.…”

Section: Related Workmentioning

confidence: 99%

An incremental constraint-based framework for task and motion planning

Dantam

Kingston

Chaudhuri

et al. 2018

The International Journal of Robotics Research

104

View full text Add to dashboard Cite

We present a new constraint-based framework for task and motion planning (TMP). Our approach is extensible, probabilistically complete, and offers improved performance and generality compared with a similar, state-of-the-art planner. The key idea is to leverage incremental constraint solving to efficiently incorporate geometric information at the task level. Using motion feasibility information to guide task planning improves scalability of the overall planner. Our key abstractions address the requirements of manipulation and object rearrangement. We validate our approach on a physical manipulator and evaluate scalability on scenarios with many objects and long plans, showing order-of-magnitude gains compared with the benchmark planner and improved scalability from additional geometric guidance. Finally, in addition to describing a new method for TMP and its implementation on a physical robot, we also put forward requirements and abstractions for the development of similar planners in the future.

show abstract

Combining Assembly Planning and Geometric Task Planning

Lallement

Cortés

Gharbi

et al. 2019

Springer Tracts in Advanced Robotics

Self Cite

View full text Add to dashboard Cite

This chapter deals with the integration of different planners that solve problems from different domains in a common context. In particular, a joint solution for structure assembly planning, symbolic task planning and geometric planning is presented and analyzed in the construction of structures with a team of aerial robots equipped with on-board manipulators in places where the access is difficult. Geometric reasoning is present at different levels in our joint solution in order to reduce the computational complexity derived from the highly dimensional space due to the many degrees of freedom of the robots and the complexity of the tasks and also to produce more robust plans even for strongly intricate problems.

show abstract

A new approach to combined symbolic-geometric backtracking in the context of human-robot interaction

Cited by 10 publications

References 14 publications

Combining symbolic and geometric planning to synthesize human-aware plans: toward more efficient combined search

Combining symbolic and geometric planning to synthesize human-aware plans: toward more efficient combined search

An incremental constraint-based framework for task and motion planning

Combining Assembly Planning and Geometric Task Planning

Contact Info

Product

Resources

About