Realizing Learned Quadruped Locomotion Behaviors through Kinematic Motion Primitives

Singla, Abhik; Bhattacharya, Shounak; Dholakiya, Dhaivat; Bhatnagar, Shalabh; Ghosal, Ashitava; Amrutur, Bharadwaj; Kolathaya, Shishir

doi:10.48550/arxiv.1810.03842

Cited by 3 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) Flat ground walking: On the flat plane, we have introduced 6 different types of gaits, trot, gallop, bound, walk, modified trot 1 and modified trot 2. We have used the basis function based approach [1] to store the information about the trajectories in a few constant values. These constant values are stored in the weight matrix (W x , W y ).…”

Section: Resultsmentioning

confidence: 99%

“…where, x i , y i are the target x, y coordinates of the i th leg. f k,j (φ i ) is the j th kinematic motion primitive [1], which essentially is a polynomial of φ i . The comparison of speeds obtained for various gaits.…”

Section: Resultsmentioning

confidence: 99%

“…The comparison of speeds obtained for various gaits. A more detailed description of the basis functions are given in [1].…”

Section: Resultsmentioning

confidence: 99%

“…With a view toward realizing state of the art walking controllers in a low-cost walking platform, we developed a quadrupedal robot called the Stoch. This manuscript primarily serves as a detailed description of the hardware and software design process and construction of this platform (see Figure 1), which complements the results that were shown in [1]. This hardware features modular central body and a five bar co-axial leg design.…”

Section: Introductionmentioning

confidence: 85%

“…In the above equations, x(φ i ), y(φ i ) represent the desired end point position values of the leg from the hip joint of the i th leg. This scheme can also be used to generate r(φ i ), θ(φ i ) in polar co-ordinates which are used in the reinforcement learning framework [1]. The constant vectors, W x,i,j , are the weights associated with the basis functions, f x,j .…”

Section: A Central Pattern Generatormentioning

confidence: 99%

See 4 more Smart Citations

Design, Development and Experimental Realization of A Quadrupedal Research Platform: Stoch

Dholakiya

Bhattacharya

Gunalan

et al. 2019

2019 5th International Conference on Control, Automation and Robotics (ICCAR)

Self Cite

View full text Add to dashboard Cite

In this paper, we present a complete description of the hardware design and control architecture of our custom built quadruped robot, called the Stoch. Our goal is to realize a robust, modular, and a reliable quadrupedal platform, using which various locomotion behaviors are explored. This platform enables us to explore different research problems in legged locomotion, which use both traditional and learning based techniques. We discuss the merits and limitations of the platform in terms of exploitation of available behaviours, fast rapid prototyping, reproduction and repair. Towards the end, we will demonstrate trotting, bounding behaviors, and preliminary results in turning. In addition, we will also show various gait transitions i.e., trot-to-turn and trot-to-bound behaviors.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

“…The comparison of speeds obtained for various gaits. A more detailed description of the basis functions are given in [1].…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 85%

Section: A Central Pattern Generatormentioning

confidence: 99%

See 3 more Smart Citations

Design, Development and Experimental Realization of A Quadrupedal Research Platform: Stoch

Dholakiya

Bhattacharya

Gunalan

et al. 2019

2019 5th International Conference on Control, Automation and Robotics (ICCAR)

Self Cite

View full text Add to dashboard Cite

show abstract

Learning Active Spine Behaviors for Dynamic and Efficient Locomotion in Quadruped Robots

Bhattacharya

Singla

Abhimanyu

et al. 2019

2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

Self Cite

View full text Add to dashboard Cite

In this work, we provide a simulation framework to perform systematic studies on the effects of spinal joint compliance and actuation on bounding performance of a 16-DOF quadruped spined robot Stoch 2. Fast quadrupedal locomotion with active spine is an extremely hard problem, and involves a complex coordination between the various degrees of freedom. Therefore, past attempts at addressing this problem have not seen much success. Deep-Reinforcement Learning seems to be a promising approach, after its recent success in a variety of robot platforms, and the goal of this paper is to use this approach to realize the aforementioned behaviors. With this learning framework, the robot reached a bounding speed of 2.1 m/s with a maximum Froude number of 2. Simulation results also show that use of active spine, indeed, increased the stride length, improved the cost of transport, and also reduced the natural frequency to more realistic values.

show abstract

Gait Library Synthesis for Quadruped Robots via Augmented Random Search

Tirumala¹,

Sagi²,

Paigwar³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, with a view toward fast deployment of learned locomotion gaits in low-cost hardware, we generate a library of walking trajectories, namely, forward trot, backward trot, side-step, and turn in our custom built quadruped robot, Stoch 2, using reinforcement learning. There are existing approaches that determine optimal policies for each time step, whereas we determine an optimal policy, in the form of endfoot trajectories, for each half walking step i.e., swing phase and stance phase. The way-points for the foot trajectories are obtained from a linear policy, i.e., a linear function of the states of the robot, and cubic splines are used to interpolate between these points. Augmented Random Search, a modelfree and gradient-free learning algorithm, is used to learn the policy in simulation. This learned policy is then deployed on hardware, yielding a trajectory in every half walking step. Different locomotion patterns are learned in simulation by enforcing a preconfigured phase shift between the trajectories of different legs. Transition from one gait to another is achieved by using a low-pass filter for the phase, and the sim-to-real transfer is improved by a linear transformation of the states obtained through regression.

show abstract

Realizing Learned Quadruped Locomotion Behaviors through Kinematic Motion Primitives

Cited by 3 publications

References 0 publications

Design, Development and Experimental Realization of A Quadrupedal Research Platform: Stoch

Design, Development and Experimental Realization of A Quadrupedal Research Platform: Stoch

Learning Active Spine Behaviors for Dynamic and Efficient Locomotion in Quadruped Robots

Gait Library Synthesis for Quadruped Robots via Augmented Random Search

Contact Info

Product

Resources

About