Organizations: Amazon Fulfillment Technologies & Robotics, Westborough MA, USA. · University of Iowa, Iowa City, IA 52240. · Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
Agile quadruped navigation in dynamic environments demands trajectories that are both dynamically feasible and provably collision-free. Most real-time planners achieve tractability through a convex reduction that requires simplified kinematic models, discarding motion that the robot can readily execute, and certify safety only at discretization points, leaving open possible inter-sample collisions with moving obstacles. We present a real-time motion planning framework that retains the fully-actuated SE(2) model of a quadruped, with its anisotropic, heading-coupled velocity bounds, and accepts the resulting nonconvexity. By parameterizing trajectories as composite Bernstein polynomials, we exploit the convex hull property to certify collision avoidance and the input bounds over the entirety of each planning horizon. Solved at online replanning rates, the optimization runs in closed loop, commanding body velocities to the locomotion controller. We validate the approach in simulation against ablations and external baselines, and in hardware experiments on a quadruped navigating among unknown moving obstacles, recovering both lateral and heading-coupled motion that simplified models exclude.
Figures & tables
Fig. 1 : Spot crossing a field of five differential-drive robots using our planner, shown at timesteps t1 – t3 as obstacles cross its path. The magenta curve is the planned trajectory, arrows indicate obstacle motion.
Fig. 4 : Benchmark environments, rendered in Isaac Sim. (a) Static condition: the 25 cylindrical obstacles are held fixed. (b) Dynamic condition: identical seeded obstacle field, each obstacle crosses laterally back-and-forth in its own lane.
planner
success
collision
timeout
solve med/p95 [ms]
mission [s]
static
holo (ours)
50/50
0
0
5.2 / 8.8
9.7
uni
49/50
0
1
3.2 / 6.4
15.5
int-vx
44/50
0
6
5.1 / 9.4
15.1
int-vy
50/50
0
0
4.1 / 8.4
16.5
layered [ 26 ]
39/50
0
11
–
24.8
TABLE I : Closed-loop results over n=50 shared seeds, comparing the full planner against its kinematic ablations (indented) and external baselines under static and dynamic obstacles. The external baselines ( layered and rmp ) run at idealized fixed rates, so solve time is not reported.
Fig. 5 : Constraint satisfaction over one corridor traversal (721 solves, 19.5 s). (a) clearance to the nearest perceived obstacle, (b) commanded vx , (c) commanded vy , (d) coupled velocity-envelope margin gell=1−(vx2/1.22)−(vy2/0.62) , (e) commanded yaw rate. Clearance is measured from odometry. t1 – t3 represent the stills from Fig. 1 .
Safe motion planning develops methods for robots and vehicles to reach goals while avoiding collisions and respecting dynamic and uncertainty constraints.
Efficiently learning safe and agile quadruped navigation in densely cluttered environments remains difficult: existing methods often lack safety and agility, or become conservative in complex scenes and require long training schedules. We propose SEA-Nav (Safe, Efficient, and Agile Navigation), a safe reinforcement learning framework for quadruped navigation in cluttered environments. A differentiable control barrier function (CBF) shield constrains the policy to produce safe velocity commands. An adaptive collision-state initialization mechanism increases the probability of learning from safety-critical near-collision experience. An action regularization term further suppresses infeasible commands for physical deployment. The policy converges after about one hour of training on a single RTX 4090 and transfers zero-shot to real-world cluttered scenes.
Shiyi Chen, Mingye Yang, Haiyi Liu +6
Tsinghua University, Beijing, China. · Imperial College London, London, UK.
Quadruped robots are increasingly expected to navigate through narrow passages, cluttered indoor scenes, and large-scale 3D unstructured environments. Existing local planners commonly approximate the robot using isotropic geometric inflation or rely on planar and elevation-map representations, leading to conservative motion in tight spaces and limited reasoning about overhanging structures. This letter presents SCAN-Planner, a spatial collision-aware local planning framework for long-range quadruped navigation. A yaw-aware twin-cylinder footprint is used to model the elongated robot body, enabling whole-body collision evaluation through sparse queries in an inflated 3D occupancy map. We further introduce a projected A* search that generates collision-free guidance on an interpolated ground-following surface, with z-gradient suppression to avoid obstacles horizontally while maintaining vertical stability. For large-scale deployment, a robot-centric sliding map with boundary fallback provides high-resolution local collision checking and recovery from local dead ends. Simulation and real-world experiments demonstrate that SCAN-Planner generates safe, smooth, and efficient trajectories in dense clutter, 3D unstructured scenes, stair traversal, and long-range navigation tasks.
Navigating dynamic and crowded environments presents significant challenges for quadruped robots due to severe sensor occlusion and unpredictable human motion. Existing approaches face a trade-off: model-based methods, such as Velocity Obstacles (VO), theoretically guarantee safety but rely on accurate obstacle motion estimates that often fail in dense crowds, while end-to-end learning methods offer robustness but lack motion prediction capability of obstacles, leading to collisions or conservative behaviors. To solve this, we propose VOP-Nav, a novel navigation system that combines the geometric safety of VO with the agile adaptability of end-to-end learning. Using only local onboard observations, our system avoids explicit obstacle detection and tracking pipelines. The VOP-Net processes multi-frame LiDAR data to implicitly encode dynamic constraints and predict a safe velocity region derived from Velocity Obstacle theory. Importantly, the VO predictions serve a dual role: they are used as input to the navigation policy during inference and as a reward signal during training to encourage safe motion. Evaluations in Isaac Gym demonstrate that VOP-Nav achieves higher success rates than all baselines while balancing locomotion speed and collision avoidance. Real-world deployment on a Unitree Go2 quadruped robot further validates the system's robustness and efficiency in complex indoor and outdoor dynamic environments.
Shuyu Wu, Zeyu Liu, Tianbao Zhang +6
Shanghai Jiao Tong University, Shanghai 200240, China · State Key Laboratory of High-end Heavy-load Robots, Midea Group, Foshan 528300, China