PyRobot: An Open-source Robotics Framework for Research and Benchmarking

Murali, Adithyavairavan; Chen, Tao; Alwala, Kalyan Vasudev; Gandhi, Dhiraj; Pinto, Lerrel; Gupta, Saurabh; Gupta, Abhinav

doi:10.48550/arxiv.1906.08236

Cited by 31 publications

(43 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is not a problem for a tall robot, such as the Fetch mobile manipulator, whose height ranges 1.096m − 1.491m (3.596f t − 4.892f t), within the throw distance of ViewSonic PA503W 0.99m − 10.98m (3.25f t − 36.02f t). However, mobile robots without upper bodies are often lower than 1m, such as TurtleBot or PyRobot [63]. Using such robots thus requires building a tall structure on the robot, or selecting a projector with a short throw distance.…”

Section: Limitationsmentioning

confidence: 99%

Projecting Robot Navigation Paths: Hardware and Software for Projected AR

Zhi-gang¹,

Parrillo²,

Wilkinson³

et al. 2021

Preprint

View full text Add to dashboard Cite

For mobile robots, mobile manipulators, and autonomous vehicles to safely navigate around populous places such as streets and warehouses, human observers must be able to understand their navigation intent. One way to enable such understanding is by visualizing this intent through projections onto the surrounding environment. But despite the demonstrated effectiveness of such projections, no open codebase with an integrated hardware setup exists. In this work, we detail the empirical evidence for the effectiveness of such directional projections, and share a robot-agnostic implementation of such projections, coded in C++ using the widely-used Robot Operating System (ROS) and rviz. Additionally, we demonstrate a hardware configuration for deploying this software, using a Fetch robot, and briefly summarize a full-scale user study that motivates this configuration. The code, configuration files (roslaunch and rviz files), and documentation are freely available on GitHub at https://github.com/umhan35/arrow projection.

show abstract

Section: Limitationsmentioning

confidence: 99%

Projecting Robot Navigation Paths: Hardware and Software for Projected AR

Zhi-gang¹,

Parrillo²,

Wilkinson³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…After teleoperating the robot in 3 − 4 loops around each space to collect trajectory data, we pick 5 goal images, and generate 20 test episodes. We use the iLQR [20] implementation from the PyRobot [21] library for our controller. In Table I, we report navigation success rates before and after we perform graph updates with 30 queries.…”

Section: E Real-world Experimentsmentioning

confidence: 99%

Lifelong Topological Visual Navigation

Wiyatno¹,

Xu²,

Paull³

2021

Preprint

View full text Add to dashboard Cite

The ability for a robot to navigate with only the use of vision is appealing due to its simplicity. Traditional visionbased navigation approaches required a prior map-building step that was arduous and prone to failure, or could only exactly follow previously executed trajectories. Newer learningbased visual navigation techniques reduce the reliance on a map and instead directly learn policies from image inputs for navigation. There are currently two prevalent paradigms: end-to-end approaches forego the explicit map representation entirely, and topological approaches which still preserve some loose connectivity of the space. However, while end-to-end methods tend to struggle in long-distance navigation tasks, topological map-based solutions are prone to failure due to spurious edges in the graph. In this work, we propose a learning-based topological visual navigation method with graph update strategies that improve lifelong navigation performance over time. We take inspiration from sampling-based planning algorithms to build image-based topological graphs, resulting in sparser graphs yet with higher navigation performance compared to baseline methods. Also, unlike controllers that learn from fixed training environments, we show that our model can be finetuned using a relatively small dataset from the realworld environment where the robot is deployed. We further assess performance of our system in real-world deployments. 1

show abstract

“…As agents trained in realistic indoor environments using the Habitat simulator are adaptable to real-world deployment [13], [14], we also deploy the proposed approach on a LoCoBot robot [38]. We employ the PyRobot interface [39] to deploy code and trained models on the robot. To enable the adaptation to the real-world environment, there are some aspects that must be taken into account during training.…”

Section: Real-world Deploymentmentioning

confidence: 99%

Focus on Impact: Indoor Exploration with Intrinsic Motivation

Bigazzi,

Landi,

Cascianelli

et al. 2021

Preprint

View full text Add to dashboard Cite

Exploration of indoor environments has recently experienced a significant interest, also thanks to the introduction of deep neural agents built in a hierarchical fashion and trained with Deep Reinforcement Learning (DRL) on simulated environments. Current state-of-the-art methods employ a dense extrinsic reward that requires the complete a priori knowledge of the layout of the training environment to learn an effective exploration policy. However, such information is expensive to gather in terms of time and resources. In this work, we propose to train the model with a purely intrinsic reward signal to guide exploration, which is based on the impact of the robot's actions on the environment. So far, impact-based rewards have been employed for simple tasks and in procedurally generated synthetic environments with countable states. Since the number of states observable by the agent in realistic indoor environments is non-countable, we include a neural-based density model and replace the traditional count-based regularization with an estimated pseudo-count of previously visited states. The proposed exploration approach outperforms DRL-based competitors relying on intrinsic rewards and surpasses the agents trained with a dense extrinsic reward computed with the environment layouts. We also show that a robot equipped with the proposed approach seamlessly adapts to point-goal navigation and real-world deployment.

show abstract

PyRobot: An Open-source Robotics Framework for Research and Benchmarking

Cited by 31 publications

References 39 publications

Projecting Robot Navigation Paths: Hardware and Software for Projected AR

Projecting Robot Navigation Paths: Hardware and Software for Projected AR

Lifelong Topological Visual Navigation

Focus on Impact: Indoor Exploration with Intrinsic Motivation

Contact Info

Product

Resources

About