skip to main content

Title: Learning to Navigate by Pushing
In this work, we investigate a form of dynamic contact-rich locomotion in which a robot pushes off from obstacles in order to move through its environment. We present a reflex-based approach that switches between optimized hand- crafted reflex controllers and produces smooth and predictable motions. In contrast to previous work, our approach does not rely on periodic movements, complex models of robot and contact dynamics, or extensive hand tuning. We demonstrate the effectiveness of our approach and evaluate its performance compared to a standard model-free RL algorithm. We identify continuous clusters of similar behaviours, which allows us to successfully transfer different push-off motions directly from simulation to a physical robot without further retraining.
; ; ; ;
Award ID(s):
Publication Date:
Journal Name:
international conference on robotics and automation (ICRA)
Page Range or eLocation-ID:
171 to 177
Sponsoring Org:
National Science Foundation
More Like this
  1. Humans use all surfaces of the hand for contact-rich manipulation. Robot hands, in contrast, typically use only the fingertips, which can limit dexterity. In this work, we leveraged a potential energy–based whole-hand manipulation model, which does not depend on contact wrench modeling like traditional approaches, to design a robotic manipulator. Inspired by robotic caging grasps and the high levels of dexterity observed in human manipulation, a metric was developed and used in conjunction with the manipulation model to design a two-fingered dexterous hand, the Model W. This was accomplished by simulating all planar finger topologies composed of open kinematic chains of up to three serial revolute and prismatic joints, forming symmetric two-fingered hands, and evaluating their performance according to the metric. We present the best design, an unconventional robot hand capable of performing continuous object reorientation, as well as repeatedly alternating between power and pinch grasps—two contact-rich skills that have often eluded robotic hands—and we experimentally characterize the hand’s manipulation capability. This hand realizes manipulation motions reminiscent of thumb–index finger manipulative movement in humans, and its topology provides the foundation for a general-purpose dexterous robot hand.

  2. In spite of substantial progress, robust and dexterous in-hand manipulation remains a robotics grand challenge. Recent research has shown that optimization of robot hand morphology for specific tasks can result in custom hand designs that are low-cost, easy to maintain, and highly capable. However, the resulting manipulation strategies may not be very robust or generalizable in real-world situations. This paper shows that robustness can be improved dramatically by optimizing controls instead of contact force / trajectories and by considering uncertainty explicitly during the optimization process. We present a evolutionary algorithm based pipeline for co-optimizing hand morphology and control strategy over families of problems and initial states in order to achieve robust in-hand manipulation. We demonstrate that this approach produces robust results which utilize all surfaces of the hand and surprising dynamic motions. We showcase the advantage of optimizing joint limit values to create robust designs. Furthermore, we demonstrate that our approach is complementary to trajectory optimization based approaches and can be utilized to improve robustness of such results as well as to create custom hand designs from scratch. Results are shown for repositioning and reorienting diverse objects relative to the palm of the hand.
  3. As robots move from the laboratory into the real world, motion planning will need to account for model uncertainty and risk. For robot motions involving intermittent contact, planning for uncertainty in contact is especially important, as failure to successfully make and maintain contact can be catastrophic. Here, we model uncertainty in terrain geometry and friction characteristics, and combine a risk-sensitive objective with chance constraints to provide a trade-off between robustness to uncertainty and constraint satisfaction with an arbitrarily high feasibility guarantee. We evaluate our approach in two simple examples: a push-block system for benchmarking and a single-legged hopper. We demonstrate that chance constraints alone produce trajectories similar to those produced using strict complementarity constraints; however, when equipped with a robust objective, we show the chance constraints can mediate a trade-off between robustness to uncertainty and strict constraint satisfaction. Thus, our study may represent an important step towards reasoning about contact uncertainty in motion planning.
  4. 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.
  5. Abstract Insects are highly capable walkers, but many questions remain regarding how the insect nervous system controls locomotion. One particular question is how information is communicated between the ‘lower level’ ventral nerve cord (VNC) and the ‘higher level’ head ganglia to facilitate control. In this work, we seek to explore this question by investigating how systems traditionally described as ‘positive feedback’ may initiate and maintain stepping in the VNC with limited information exchanged between lower and higher level centers. We focus on the ‘reflex reversal’ of the stick insect femur-tibia joint between a resistance reflex (RR) and an active reaction in response to joint flexion, as well as the activation of populations of descending dorsal median unpaired (desDUM) neurons from limb strain as our primary reflex loops. We present the development of a neuromechanical model of the stick insect ( Carausius morosus ) femur-tibia (FTi) and coxa-trochanter joint control networks ‘in-the-loop’ with a physical robotic limb. The control network generates motor commands for the robotic limb, whose motion and forces generate sensory feedback for the network. We based our network architecture on the anatomy of the non-spiking interneuron joint control network that controls the FTi joint, extrapolated network connectivity based on known muscle responses,more »and previously developed mechanisms to produce ‘sideways stepping’. Previous studies hypothesized that RR is enacted by selective inhibition of sensory afferents from the femoral chordotonal organ, but no study has tested this hypothesis with a model of an intact limb. We found that inhibiting the network’s flexion position and velocity afferents generated a reflex reversal in the robot limb’s FTi joint. We also explored the intact network’s ability to sustain steady locomotion on our test limb. Our results suggested that the reflex reversal and limb strain reinforcement mechanisms are both necessary but individually insufficient to produce and maintain rhythmic stepping in the limb, which can be initiated or halted by brief, transient descending signals. Removing portions of this feedback loop or creating a large enough disruption can halt stepping independent of the higher-level centers. We conclude by discussing why the nervous system might control motor output in this manner, as well as how to apply these findings to generalized nervous system understanding and improved robotic control.« less