EGO-Planner
A lightweight gradient-based local planner for quadrotors that eliminates ESDF construction, achieving planning times around 1ms.
What is EGO-Planner?
EGO-Planner is a gradient-based local planner for quadrotors that avoids Euclidean Signed Distance Field (ESDF) construction to achieve extremely fast planning times. It solves the problem of computational bottlenecks in real-time drone navigation by providing a lightweight alternative to ESDF-dependent planners, with total planning times around 1ms.
Researchers and developers working on autonomous drone navigation, particularly those focused on real-time local planning for quadrotors in ROS-based systems.
Developers choose EGO-Planner for its elimination of ESDF computation—a major performance bottleneck—resulting in significantly faster planning times (≈1ms) compared to state-of-the-art methods, while maintaining trajectory quality and safety.
Overview
EGO-Planner is an ESDF-free gradient-based local planner designed for quadrotor navigation. It significantly reduces computation time compared to state-of-the-art methods by avoiding the computationally expensive Euclidean Signed Distance Field (ESDF) construction, enabling real-time performance with total planning times around 1ms.
Key Features
- ESDF-Free Planning — Eliminates the need to compute Euclidean Signed Distance Fields, drastically reducing computational overhead.
- Lightweight Gradient-Based Optimization — Uses a gradient-based approach for efficient local trajectory generation.
- GPU/CPU Versatility — Offers both GPU and CPU versions of its local sensing module for depth image generation or pointcloud processing.
- Fast Computation — Achieves planning times of approximately 1ms, suitable for real-time drone control.
- Simulation-Ready — Includes a lightweight quadrotor simulator and supports integration with sensors like Intel RealSense for hardware testing.
Philosophy
EGO-Planner prioritizes computational efficiency and real-time performance by removing the ESDF construction bottleneck, making advanced local planning accessible for resource-constrained aerial robotics applications.
Use Cases
Best For
- Real-time local planning for autonomous quadrotors
- Reducing computational overhead in drone navigation stacks
- Academic research on gradient-based motion planning
- ROS-based drone simulation and testing
- Projects requiring sub-millisecond planning times
- Integrating with depth sensors like Intel RealSense for hardware deployment
Not Ideal For
- Projects requiring Euclidean Signed Distance Fields for global mapping or detailed environmental analysis
- Swarm robotics applications where multi-drone coordination is essential
- Teams operating outside the ROS ecosystem or planning to use ROS2 without significant adaptation
- Environments with highly dynamic obstacles that benefit from continuous distance field updates
Pros & Cons
Pros
Eliminates the computationally expensive ESDF construction, reducing total planning time to around 1ms, as highlighted in the README for real-time quadrotor navigation.
Offers both GPU and CPU versions for the local sensing module, allowing flexibility in deployment on different hardware setups, with configurable CUDA support for depth image generation.
Includes a lightweight quadrotor simulator and supports integration with sensors like Intel RealSense, facilitating easy testing and hardware deployment without extensive setup.
Achieves planning times significantly faster than state-of-the-art methods by avoiding ESDF bottlenecks, enabling sub-millisecond performance suitable for resource-constrained applications.
Cons
The README explicitly recommends using EGO-Swarm for improved robustness and safety, making EGO-Planner less ideal for new projects despite its performance benefits.
Configuring the GPU version requires manual adjustments to CUDA flags and compatibility checks for NVIDIA cards, which can be error-prone and time-consuming, as noted in the installation instructions.
Tied to specific Ubuntu and ROS versions (16.04, 18.04, 20.04), with ROS2 support only available in a separate branch of EGO-Swarm, limiting flexibility for teams on newer or different systems.
Frequently Asked Questions
Related Projects
pinocchioA fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives
casADiCasADi is a symbolic framework for numeric optimization implementing automatic differentiation in forward and reverse modes on sparse matrix-valued computational graphs. It supports self-contained C-code generation and interfaces state-of-the-art codes such as SUNDIALS, IPOPT etc. It can be used from C++, Python, Matlab/Octave, Julia or Javascript
omplThe Open Motion Planning Library (OMPL)
path_plannerHybrid A* Path Planner for the KTH Research Concept Vehicle
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.