Search

A²R Lab
  • Home
  • Research Projects
  • Publications
  • People
  • Join Us
  • PI's Courses
  • Barnard CS
Avatar

Barnard College, Columbia University

The Accessible and Accelerated Robotics Lab (A²R Lab)

The A²R Lab at Barnard College, Columbia University, focuses on developing and implementing open-source algorithms for dynamic motion planning and control of robots by exploiting both the mathematical structure of algorithms and the design of computational platforms. As such, our research is at the intersection of Robotics and Computer Architecture, Embedded Systems, Numerical Optimization, and Machine Learning.

We also want to improve the accessibility of STEM education. We therefore undertake research to understand and improve diversity, equity, inclusion, and belonging in STEM education globally and explore ways to design new interdisciplinary, project-based, open-access courses that lower the barrier to entry of cutting edge topics like robotics and embedded machine learning.

Featured Publications

TinyMPC: Model-Predictive Control on Resource-Constrained Microcontrollers

Model-predictive control (MPC) is a powerful tool for controlling highly dynamic robotic systems subject to complex constraints. However, MPC is computationally demanding, and is often impractical to implement on small, resource-constrained robotic platforms. We present TinyMPC, a high-speed MPC solver with a low memory footprint targeting the microcontrollers common on small robots. Our approach is based on the alternating direction method of multipliers (ADMM) and leverages the structure of the MPC problem for efficiency. We demonstrate TinyMPC both by benchmarking against the state-of-the-art solver OSQP, achieving nearly an order of magnitude speed increase, as well as through hardware experiments on a 27 g quadrotor, demonstrating high-speed trajectory tracking and dynamic obstacle avoidance.
Anoushka Alavilli , Khai Nguyen , Sam Schoedel , Brian Plancher , Zachary Manchester
PDF Code Video Website

MPCGPU: Real-Time Nonlinear Model Predictive Control through Preconditioned Conjugate Gradient on the GPU

We introduce MPCGPU, a GPU-accelerated, real-time NMPC solver that leverages an accelerated preconditioned conjugate gradient (PCG) linear system solver at its core. We show that MPCGPU increases the scalability and real-time performance of NMPC, solving larger problems, at faster rates. In particular, for tracking tasks using the Kuka IIWA manipulator, MPCGPU is able to scale to kilohertz control rates with trajectories as long as 512 knot points. This is driven by a custom PCG solver which outperforms state-of-the-art, CPU-based, linear system solvers by at least 10x for a majority of solves and 3.6x on average.
Emre Adabag , Miloni Atal , William Gerard , Brian Plancher
PDF Code

RoboShape: Using Topology Patterns to Scalably and Flexibly Deploy Accelerators Across Robots

We present RoboShape, an accelerator framework that leverages two topology-based computational patterns that scale with robot size: (1) topology traversals, and (2) large topology-based matrices. Using these patterns and building on prior work, we expose opportunities to directly use robot topology to inform architectural mechanisms including task scheduling and allocation, data placement, block matrix operations, and sparse I/O data. For the topologically-diverse iiwa manipulator, HyQ quadruped, and Baxter torso robots, RoboShape accelerators on an FPGA provide a 4.0x to 4.4x speedup in compute latency over CPU and a 8.0x to 15.1x speedup over GPU for the dynamics gradients, a key bottleneck preventing online execution of nonlinear optimal motion control for legged robots. Taking a broader view, for topology-based applications, RoboShape enables analysis of performance and resource utilization tradeoffs that will be critical to managing resources across accelerators in future full robotics domain-specific SoCs.
Sabrina M. Neuman , Radhika Ghosal , Thomas Bourgeat , Brian Plancher , Vijay Janapa Reddi
PDF Video DOI

Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion

Deep reinforcement learning (DRL) is one of the most powerful tools for synthesizing complex robotic behaviors. But training DRL models is incredibly compute and memory intensive, requiring large training datasets and replay buffers to achieve performant results. This poses a challenge for the next generation of field robots that will need to learn on the edge to adapt to their environment. In this paper, we begin to address this issue through observation space quantization. We evaluate our approach using four simulated robot locomotion tasks and two state-of-the-art DRL algorithms, the on-policy Proximal Policy Optimization (PPO) and off-policy Soft Actor-Critic (SAC) and find that observation space quantization reduces overall memory costs by as much as 4.2x without impacting learning performance.
Lev Grossman , Brian Plancher
PDF Video DOI Code

GRiD: GPU-Accelerated Rigid Body Dynamics with Analytical Gradients

We introduce and release GRiD, an open-source, GPU-accelerated library for computing rigid body dynamics with analytical gradients. GRiD was designed to accelerate nonlinear trajectory optimization through optimized code generation, GRiD provides as much as a 7.2x speedup over a state-of-the-art, multi-threaded CPU implementation and maintains as much as a 2.5x speedup when accounting for I/O overhead.
Brian Plancher , Sabrina M. Neuman , Radhika Ghosal , Scott Kuindersma , Vijay Janapa Reddi
PDF Code Poster Slides Video DOI Benchmark Experiments

Robomorphic Computing: A Design Methodology for Domain-Specific Accelerators Parameterized by Robot Morphology

We introduce robomorphic computing; a methodology to transform robot morphology into a customized hardware accelerator morphology. In this work, we (i) present this design methodology; (ii) use the methodology to generate a parameterized accelerator design for the gradient of rigid body dynamics; (iii) evaluate FPGA and synthesized ASIC implementations; and (iv) describe how the design can be automatically customized for other robot models. Our FPGA accelerator achieves speedups of 8x and 86x over CPU and GPU latency, and maintains an overall speedup of 1.9x to 2.9x deployed in an end-to-end coprocessor system. ASIC synthesis indicates an additional factor of 7.2x.
Sabrina M. Neuman , Brian Plancher , Thomas Bourgeat , Thierry Tambe , Srini Devadas , Vijay Janapa Reddi
PDF Slides Video DOI Extended Abstract

Accelerating Robot Dynamics Gradients on a CPU, GPU, and FPGA

In this paper, we detail the designs of three faster than state-of-the-art implementations of the gradient of rigid body dynamics on a CPU, GPU, and FPGA. Our optimized FPGA and GPU implementations provide as much as a 3.0x end-to-end speedup over our optimized CPU implementation by refactoring the algorithm to exploit its computational features, e.g., parallelism at different granularities.
Brian Plancher , Sabrina M. Neuman , Thomas Bourgeat , Scott Kuindersma , Srini Devadas , Vijay Janapa Reddi
PDF Code Slides Video DOI

Realtime Model Predictive Control using Parallel DDP on a GPU

In this extended abstract we extend our previous work by using our Parallel DDP implementation for MPC on a physical Kuka arm. We demonstrated the feasibility of this approach in the presence of model discrepancies and communication delays between the robot and GPU and found that higher control rates generally lead to better tracking performance across a range of parallelization options.
Brian Plancher , Scott Kuindersma
PDF Code Poster Video

Privacy

© 2023 Brian Plancher · Powered by the Academic theme for Hugo.

Cite
Copy Download