https://github.com/translearn/safemotions
[Humanoids 2022] Learning Collision-free and Torque-limited Robot Trajectories based on Alternative Safe Behaviors
https://github.com/translearn/safemotions
humanoids python robotics safe-reinforcement-learning
Last synced: 5 months ago
JSON representation
[Humanoids 2022] Learning Collision-free and Torque-limited Robot Trajectories based on Alternative Safe Behaviors
- Host: GitHub
- URL: https://github.com/translearn/safemotions
- Owner: translearn
- License: other
- Created: 2021-02-28T08:18:53.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2025-12-18T08:30:20.000Z (6 months ago)
- Last Synced: 2025-12-21T15:57:08.092Z (6 months ago)
- Topics: humanoids, python, robotics, safe-reinforcement-learning
- Language: Python
- Homepage:
- Size: 19.7 MB
- Stars: 23
- Watchers: 1
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Learning Collision-free and Torque-limited Robot Trajectories based on Alternative Safe Behaviors
[](https://www.humanoids2022.org/)
[](https://arxiv.org/abs/2103.03793)
[](https://github.com/translearn/safemotions/issues/)
This repository provides the code to learn torque-limited and collision-free robot trajectories without exceeding limits on the position, velocity, acceleration and jerk of each robot joint. \
**Note:** A follow-up work which considers moving obstacles can be found in the repository [safeMotionsRisk](https://github.com/translearn/safeMotionsRisk).
## Installation
To use the code, clone the repository with:
git clone https://github.com/translearn/safeMotions.git
The required dependencies can be installed by running:
pip install -r requirements.txt
## Trajectory generation [](https://colab.research.google.com/github/translearn/notebooks/blob/main/safemotions_random_agent_demo.ipynb)
To generate a random trajectory with a single robot run
python safemotions/random_agent.py --use_gui --check_braking_trajectory_collisions --check_braking_trajectory_torque_limits --torque_limit_factor=0.6 --plot_trajectory
For a demonstration scenario with two robots run
python safemotions/random_agent.py --use_gui --check_braking_trajectory_collisions --robot_scene=1
Collision-free trajectories for three robots can be generated by running
python safemotions/random_agent.py --use_gui --check_braking_trajectory_collisions --robot_scene=2
## Pretrained networks [](https://colab.research.google.com/github/translearn/notebooks/blob/main/safemotions_trained_networks_demo.ipynb)
Various pretrained networks for reaching randomly sampled target points are provided. \
Make sure you use ray==1.4.1 to open the pretrained networks.
### Industrial robots
To generate and plot trajectories for a reaching task with a single industrial robot run
```bash
python safemotions/evaluate.py --use_gui --plot_trajectory --plot_actual_torques --checkpoint=industrial/one_robot/collision
```
Trajectories for two and three industrial robots with alternating target points can be generated by running
```bash
python safemotions/evaluate.py --use_gui --checkpoint=industrial/two_robots/collision/alternating
```
and
```bash
python safemotions/evaluate.py --use_gui --checkpoint=industrial/three_robots/collision/alternating
```
### Humanoid robots
ARMAR 6
ARMAR 6x4
Alternating target points
--checkpoint=humanoid/armar6/collision/alternating
--checkpoint=humanoid/armar6_x4/collision/alternating
Simultaneous target points
--checkpoint=humanoid/armar6/collision/simultaneous
--checkpoint=humanoid/armar6_x4/collision/simultaneous
Single target point
--checkpoint=humanoid/armar6/collision/single
--checkpoint=humanoid/armar6_x4/collision/single
## Training
Networks can also be trained from scratch. For instance, a reaching task with a single robot can be learned by running
```bash
python safemotions/train.py --logdir=safemotions_training --name=industrial_one_robot_collision --robot_scene=0 --online_trajectory_time_step=0.1 --hidden_layer_activation=swish --online_trajectory_duration=8.0 --obstacle_scene=3 --use_target_points --target_point_sequence=0 --target_point_cartesian_range_scene=0 --target_link_offset="[0, 0, 0.126]" --target_point_radius=0.065 --obs_add_target_point_pos --obs_add_target_point_relative_pos --check_braking_trajectory_collisions --closest_point_safety_distance=0.01 --acc_limit_factor_braking=1.0 --jerk_limit_factor_braking=1.0 --punish_action --action_punishment_min_threshold=0.95 --action_max_punishment=0.4 --target_point_reached_reward_bonus=5 --pos_limit_factor=1.0 --vel_limit_factor=1.0 --acc_limit_factor=1.0 --jerk_limit_factor=1.0 --torque_limit_factor=1.0 --punish_braking_trajectory_min_distance --braking_trajectory_min_distance_max_threshold=0.05 --braking_trajectory_max_punishment=0.5 --last_layer_activation=tanh --solver_iterations=50 --normalize_reward_to_initial_target_point_distance --collision_check_time=0.033 --iterations_per_checkpoint=50 --time=200
```
## Publication
Further details can be found in the following [publication](https://arxiv.org/abs/2103.03793):
```
title={Learning Collision-free and Torque-limited Robot Trajectories based on Alternative Safe Behaviors},
booktitle={2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)},
author={Kiemel, Jonas and Kröger, Torsten},
year={2022},
pages={223-230},
doi={10.1109/Humanoids53995.2022.10000077}
```
[](https://youtu.be/U2OWsQrt-40)
## Disclaimer
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.