Humanoid navigation in uneven terrain using learned estimates of traversability

Lin, Yu-Chi; Berenson, Dmitry

doi:10.1109/humanoids.2017.8239531

Cited by 13 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic planning using a reduced robot model has recently shown promising results [21] but has not been evaluated in deployment scenarios. Other work on navigation planning specifically for legged robots either only considers cases of obstacle avoidance on flat terrain [22], [23] or does additional contact planning, which pushes computational complexity past the real-time mark [24], [25], [26].…”

Section: Related Workmentioning

confidence: 99%

Rough Terrain Navigation for Legged Robots using Reachability Planning and Template Learning

Wellhausen

Hutter

2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Navigation planning for legged robots has distinct challenges compared to wheeled and tracked systems due to the ability to lift legs off the ground and step over obstacles. While most navigation planners assume a fixed traversability value for a single terrain patch, we overcome this limitation by proposing a reachability-based navigation planner for legged robots. We approximate the robot morphology by a set of reachability and body volumes, assuming that the reachability volumes need to always be in contact with the environment, while the body should be contact-free. We train a convolutional neural network to predict foothold scores which are used to restrict geometries which are considered suitable to step on. Using this representation, we propose a navigation planner based on probabilistic roadmaps. Through validation of only low-cost graph edges during graph expansion and an adaptive sampling scheme based on roadmap node density, we achieve real-time performance with fast update rates even in cluttered and narrow environments. We thoroughly validate the proposed navigation planner in simulation and demonstrate its performance in real-world experiments on the quadruped ANYmal.

show abstract

Section: Related Workmentioning

confidence: 99%

Rough Terrain Navigation for Legged Robots using Reachability Planning and Template Learning

Wellhausen

Hutter

2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…Each action is a foot contact transition, which means moving one foot to a new pose. Contact transitions are predefined as a discrete set of foot projections, shown in Figure 2(a), and we adopt the contact projection approach in [38].…”

Section: Anytime Discrete-search Contact Plannermentioning

confidence: 99%

Robust Humanoid Contact Planning With Learned Zero- and One-Step Capturability Prediction

Lin

Righetti

Berenson

2020

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

Humanoid robots maintain balance and navigate by controlling the contact wrenches applied to the environment. While it is possible to plan dynamically-feasible motion that applies appropriate wrenches using existing methods, a humanoid may also be affected by external disturbances. Existing systems typically rely on controllers to reactively recover from disturbances. However, such controllers may fail when the robot cannot reach contacts capable of rejecting a given disturbance. In this paper, we propose a search-based footstep planner which aims to maximize the probability of the robot successfully reaching the goal without falling under disturbances. The planner considers not only the poses of the planned contact sequence, but also alternative contacts near the planned contact sequence that can be used to recover from external disturbances. Although this additional consideration significantly increases the computation load, we train neural networks to efficiently predict multi-contact zero-step and one-step capturability, which allows the planner to generate robust contact sequences efficiently. Our results show that our approach generates footstep sequences that are more robust to external disturbances than a conventional footstep planner in four challenging scenarios.

show abstract

“…V. ANYTIME DISCRETE-SEARCH CONTACT PLANNER We build on the anytime discrete-search contact planner described in [36] with substantial modification on the edge cost and heuristic computation. We formulate the contact planning problem as a graph search.…”

Section: Centroidal Momentum Dynamics Optimizationmentioning

confidence: 99%

“…An action is either moving one end-effector to a new contact pose, or breaking one palm contact. The contact transitions are based on a predefined discrete transition model, shown in Figure 2, and we adopt the contact projection scheme in [36]. The edge cost of each action from a state s to a state s is defined as…”

Section: Centroidal Momentum Dynamics Optimizationmentioning

confidence: 99%

Efficient Humanoid Contact Planning using Learned Centroidal Dynamics Prediction

Lin

Ponton

Righetti

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Humanoid robots dynamically navigate an environment by interacting with it via contact wrenches exerted at intermittent contact poses. Therefore, it is important to consider dynamics when planning a contact sequence. Traditional contact planning approaches assume a quasi-static balance criterion to reduce the computational challenges of selecting a contact sequence over a rough terrain. This however limits the applicability of the approach when dynamic motions are required, such as when walking down a steep slope or crossing a wide gap. Recent methods overcome this limitation with the help of efficient mixed integer convex programming solvers capable of synthesizing dynamic contact sequences. Nevertheless, its exponential-time complexity limits its applicability to short time horizon contact sequences within small environments. In this paper, we go beyond current approaches by learning a prediction of the dynamic evolution of the robot centroidal momenta, which can then be used for quickly generating dynamically robust contact sequences for robots with arms and legs using a search-based contact planner. We demonstrate the efficiency and quality of the results of the proposed approach in a set of dynamically challenging scenarios.

show abstract

Humanoid navigation in uneven terrain using learned estimates of traversability

Cited by 13 publications

References 19 publications

Rough Terrain Navigation for Legged Robots using Reachability Planning and Template Learning

Rough Terrain Navigation for Legged Robots using Reachability Planning and Template Learning

Robust Humanoid Contact Planning With Learned Zero- and One-Step Capturability Prediction

Efficient Humanoid Contact Planning using Learned Centroidal Dynamics Prediction

Contact Info

Product

Resources

About